© 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. 21-GEMMASCOPE-RES-16K
    11. 1803
    Prev
    Next
    INDEX
    Explanations

    quotes or statements from authors or reviews

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ."));
    -0.79
     CreateTagHelper
    -0.77
     "));
    -0.75
    :");
    -0.73
    \{\\
    -0.72
    ...');
    -0.72
    ...");
    -0.70
     '))
    -0.69
     الرياضيه
    -0.69
    =");
    -0.69
    POSITIVE LOGITS
     -
    1.51
     —
    1.50
     –
    1.50
     --
    1.36
    ―
    1.29
    —
    1.25
     ~
    1.23
     ―
    1.23
    --
    1.19
    –
    1.17
    Activations Density 0.169%

    No Known Activations