© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 13897
    Prev
    Next
    INDEX
    Explanations

    structural elements of JavaScript code

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

    Code syntax, especially parentheses and semicolons

    np_acts-logits-general · gemini-2.0-flash

    IFN-γ and scientific sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prediction
    -1.02
     חיצוניים
    -0.99
     predictions
    -0.97
     Predict
    -0.95
     Prediction
    -0.94
     predicting
    -0.92
     predict
    -0.92
     Predictions
    -0.86
     predicts
    -0.84
    Predict
    -0.83
    POSITIVE LOGITS
     let
    0.46
    ];
    0.43
    RTCF
    0.42
     bas
    0.42
    let
    0.42
     Bas
    0.41
    const
    0.41
    pha
    0.41
     ;
    0.40
    ;#
    0.40
    Activations Density 0.193%

    No Known Activations