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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9583
    Prev
    Next
    INDEX
    Explanations

    code elements and terms related to UI components and data handling in programming contexts

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

    variable names and identifiers in code, particularly those that appear in method calls, object properties, and function parameters.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
     un
    -0.51
     hu
    -0.51
     hy
    -0.51
     BRID
    -0.51
     automatically
    -0.50
     RELATION
    -0.50
     respecting
    -0.50
     Facebook
    -0.49
     critically
    -0.49
     brimming
    -0.49
    POSITIVE LOGITS
    ImageContext
    0.54
    Viitteet
    0.51
     kasarigan
    0.48
    Дереккөздер
    0.47
    Portály
    0.46
    Personendaten
    0.45
    Примітки
    0.44
    rungsseite
    0.43
     ModelExpression
    0.43
    Obrázky
    0.42
    Activations Density 0.480%

    No Known Activations