© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2092
    Prev
    Next
    INDEX
    Explanations

    references to data types and variables in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    method calls and object property access using dot notation in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    method calls on class or object names in programming code, particularly when accessing static methods or properties (indicated by the dot notation).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to programming-language standard library identifiers—class and method names (often in dot notation) in Java/C#-style code.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hdashline
    -0.64
    nextDouble
    -0.48
    toMatchSnapshot
    -0.47
     Autorizaciones
    -0.46
    principalColumn
    -0.42
     defaultstate
    -0.41
    AutoField
    -0.40
    recated
    -0.39
    InjectAttribute
    -0.39
    kháu
    -0.37
    POSITIVE LOGITS
     intptr
    0.57
    tvguidetime
    0.47
     combineReducers
    0.47
    rawDesc
    0.43
    شهاد
    0.43
    ⟬
    0.43
    ASIN
    0.41
    saraba
    0.41
     AssemblyCulture
    0.41
    +#+#
    0.40
    Activations Density 0.154%

    No Known Activations