© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 9963
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting elements commonly found in scientific documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.73
    /#{
    -0.61
     (
    -0.54
     Peterson
    -0.52
    invokeLater
    -0.52
     odst
    -0.52
    eaking
    -0.50
    nya
    -0.49
    BindingSource
    -0.49
    UniformLocation
    -0.49
    POSITIVE LOGITS
    featureID
    0.85
    ])));
    0.67
    ]++;
    0.64
    )++;
    0.63
    __;
    0.62
    ftagPool
    0.62
    ]--;
    0.62
    }{*}{}
    0.60
    drawSprites
    0.59
    gonic
    0.58
    Activations Density 0.951%

    No Known Activations