© 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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 12980
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structures within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.42
    ”.
    -0.40
    ’
    -0.38
    KEYCODE
    -0.38
    cshtml
    -0.37
     fili
    -0.37
     relever
    -0.36
    .”
    -0.36
     ben
    -0.36
     виправивши
    -0.36
    POSITIVE LOGITS
     myſelf
    0.72
     Efq
    0.71
    AxisAlignment
    0.70
    rungsseite
    0.69
    msgTypes
    0.69
     发表于
    0.68
     مرئيه
    0.67
     Theſe
    0.67
     whoſe
    0.67
     houſe
    0.65
    Activations Density 0.377%

    No Known Activations