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. 10-GEMMASCOPE-RES-16K
    6. 12976
    Prev
    Next
    INDEX
    Explanations

    event-related information and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FBref
    -0.50
     tasca
    -0.49
     vuo
    -0.49
    oustic
    -0.49
     scena
    -0.47
    صال
    -0.46
    omotor
    -0.46
    asaki
    -0.45
    enital
    -0.45
    Output
    -0.44
    POSITIVE LOGITS
     vacation
    0.85
    vacation
    0.76
     समीक्षक
    0.73
    uxxxx
    0.73
     campaign
    0.72
     ویکی‌پدیای
    0.71
     Vacation
    0.71
     vacations
    0.70
     summer
    0.68
    stay
    0.66
    Activations Density 0.474%

    No Known Activations