© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 4648
    Prev
    Next
    INDEX
    Explanations

    code block structures and syntax in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ()=>{
    -0.65
    ={()=>
    -0.60
    [:,:,
    -0.58
    ']?>
    -0.57
    },{
    
    -0.56
     ()=>
    -0.55
    ({_
    -0.54
     OMITBAD
    -0.51
    ,:]
    -0.50
     Afterwards
    -0.50
    POSITIVE LOGITS
    AddTagHelper
    0.53
    RenderAtEndOf
    0.48
    ViewImports
    0.48
    jspb
    0.44
    nloa
    0.43
    AndEndTag
    0.42
     Chwiliwch
    0.41
    routeProvider
    0.40
    AnchorTagHelper
    0.39
     surla
    0.39
    Activations Density 0.074%

    No Known Activations