© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 9823
    Prev
    Next
    INDEX
    Explanations

    the presence of numerical data and classifications in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Chham
    -0.57
    [];
    
    -0.54
    loze
    -0.51
    '}),
    -0.51
    */),
    -0.50
    encodeWith
    -0.50
    ())),
    -0.49
    ")),
    -0.48
     ζωή
    -0.48
    []){
    -0.48
    POSITIVE LOGITS
    первых
    1.04
     Wiktionnaire
    0.78
     Firstly
    0.61
     firstly
    0.61
     einerseits
    0.61
    gathered
    0.59
     reasons
    0.57
     resultCode
    0.56
    一方面
    0.54
    fortawesome
    0.54
    Activations Density 0.362%

    No Known Activations