© 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. 1-GEMMASCOPE-RES-16K
    11. 4967
    Prev
    Next
    INDEX
    Explanations

    terms related to electronic devices and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.97
     defaultstate
    -0.85
    帖最后由
    -0.75
    contentLoaded
    -0.70
    elemField
    -0.70
    GrantedAuthority
    -0.69
    VolleyError
    -0.69
    sidemargin
    -0.67
     Процитовано
    -0.65
    Izvori
    -0.63
    POSITIVE LOGITS
     electronic
    2.09
    Electronic
    1.88
    electronic
    1.86
     Electronic
    1.85
     ELECTRONIC
    1.69
     digital
    1.55
     electronically
    1.50
     virtual
    1.33
    digital
    1.27
     elektronik
    1.26
    Activations Density 0.134%

    No Known Activations