© 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. 20-GEMMASCOPE-RES-16K
    6. 7267
    Prev
    Next
    INDEX
    Explanations

    programming-related parameters, particularly in function definitions and method calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Италијани
    -0.49
    ientôt
    -0.41
    了过来
    -0.40
     Савезне
    -0.40
     soon
    -0.40
    etc
    -0.39
    stdc
    -0.37
    reportWebVitals
    -0.37
     internally
    -0.37
     indeed
    -0.37
    POSITIVE LOGITS
    param
    0.78
    ivar
    0.57
    hdashline
    0.56
    脚注の使い方
    0.56
    ArgsConstructor
    0.56
    HasIndex
    0.55
     AttributeSet
    0.53
    togram
    0.53
    Rptr
    0.52
     {*}
    0.52
    Activations Density 0.026%

    No Known Activations