Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 3889
    Prev
    Next
    INDEX
    Explanations

    references to scientific measurements and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.50
    ScopeManager
    -0.49
     buyer
    -0.49
     PyTuple
    -0.47
     buyers
    -0.47
     Buyer
    -0.46
    पाल
    -0.46
    ForValue
    -0.45
    moveToNext
    -0.45
     للمعارف
    -0.44
    POSITIVE LOGITS
    rrggbb
    0.69
    InitVars
    0.66
     समीक्षक
    0.66
     kasarigan
    0.64
    kháu
    0.64
     marinho
    0.63
     feedbacks
    0.63
    లాలు
    0.63
     vulné
    0.62
     aerosols
    0.60
    Activations Density 0.531%

    No Known Activations