© 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. 3567
    Prev
    Next
    INDEX
    Explanations

    method calls in code

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

    method names and function calls in Java code.

    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
    Personendaten
    -0.70
    styleable
    -0.67
    UnusedPrivate
    -0.61
    ConstraintMaker
    -0.59
     Waray
    -0.59
     VIAF
    -0.58
     disponibilités
    -0.56
    IBOutlet
    -0.55
    insee
    -0.53
    Чыганаклар
    -0.51
    POSITIVE LOGITS
    imed
    0.40
    scribers
    0.37
    ../../
    0.36
    ../../../
    0.36
    < 
    0.36
    XmlSchema
    0.33
     BrowserModule
    0.33
    Identyfik
    0.33
    CrossRef
    0.32
     circun
    0.32
    Activations Density 0.183%

    No Known Activations