© 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. 17-GEMMASCOPE-RES-16K
    6. 6978
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to administrative or legal structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.57
    herin
    -0.56
     Chwiliwch
    -0.56
     Meksiku
    -0.55
    #
    -0.55
    ksom
    -0.54
    ั้น
    -0.54
    lgari
    -0.53
     mxArray
    -0.53
    UCKY
    -0.53
    POSITIVE LOGITS
     of
    2.44
    of
    1.08
     của
    1.06
    ของ
    1.00
     Of
    0.95
    Of
    0.88
    의
    0.76
     ofthe
    0.75
     ofre
    0.72
     των
    0.69
    Activations Density 1.662%

    No Known Activations