© 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. 20-GEMMASCOPE-RES-16K
    6. 13294
    Prev
    Next
    INDEX
    Explanations

    key concepts and terminologies related to research and analysis

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

    Followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    goal, need, importance, methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    \{\\
    -0.76
    CodedInputStream
    -0.72
    >");
    
    -0.70
    InitVars
    -0.69
    ']):
    -0.68
    //};
    -0.68
    )':
    -0.67
    !");
    -0.66
    /');
    -0.66
    /");
    -0.66
    POSITIVE LOGITS
    :
    1.52
    —
    1.40
     –
    1.39
     —
    1.34
     -
    1.25
     namely
    1.24
     iaitu
    1.24
     --
    1.23
    ——
    1.21
    --
    1.18
    Activations Density 0.660%

    No Known Activations