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. 15-GEMMASCOPE-RES-16K
    6. 4439
    Prev
    Next
    INDEX
    Explanations

    terminology related to advocacy and proactive measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.90
     Fet
    -0.83
     Montagu
    -0.81
     Magnetism
    -0.81
     lòng
    -0.81
     Melch
    -0.79
     parishes
    -0.73
    CopyWith
    -0.72
     Etsy
    -0.72
    cameras
    -0.72
    POSITIVE LOGITS
     PRO
    1.18
    Pro
    1.14
     Pro
    1.12
    PRO
    0.97
     pro
    0.95
    pro
    0.94
     propOrder
    0.91
     Pros
    0.83
    Про
    0.81
    )))));
    0.80
    Activations Density 0.283%

    No Known Activations