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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16052
    Prev
    Next
    INDEX
    Explanations

    structured data formats or syntax related to programming languages

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

    Filenames, model files, and file paths

    np_acts-logits-general · gemini-2.0-flash

    file paths and names

    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
    ?',
    -0.76
    >";
    
    -0.75
    %");
    -0.75
     ?";
    -0.74
    )';
    -0.73
    :],
    -0.72
    [];
    
    -0.71
    ?";
    -0.71
    !';
    -0.71
    ]}"
    -0.69
    POSITIVE LOGITS
     betweenstory
    0.73
    _
    0.64
     Chriſt
    0.64
    .
    0.62
     Theſe
    0.62
     ſeveral
    0.59
     experimento
    0.59
     reaſon
    0.58
     ſche
    0.58
     Anſ
    0.58
    Activations Density 0.377%

    No Known Activations