© 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. 15683
    Prev
    Next
    INDEX
    Explanations

    numerical data or references

    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
    <bos>
    -0.85
    ,:);
    -0.83
    Personensuche
    -0.77
    ussis
    -0.73
     NDEBUG
    -0.71
     Verso
    -0.70
    Vea
    -0.69
    endphp
    -0.67
     Versace
    -0.64
     électron
    -0.63
    POSITIVE LOGITS
     three
    1.25
    3
    1.25
    three
    1.19
     Three
    1.14
    Three
    1.10
    THREE
    1.08
     THREE
    1.00
     threes
    0.98
    4
    0.97
     trois
    0.97
    Activations Density 0.657%

    No Known Activations