© 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. 10-GEMMASCOPE-RES-16K
    6. 11571
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries, particularly those starting with "What" or "How"

    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
     صوتيه
    -0.90
    expandindo
    -0.84
     समीक्षक
    -0.79
    principalColumn
    -0.77
    iestety
    -0.76
    sizeCache
    -0.74
    دانشنامهٔ
    -0.73
     ComVisible
    -0.71
    äten
    -0.68
    HasForeignKey
    -0.68
    POSITIVE LOGITS
     What
    1.16
    What
    1.11
     How
    1.10
    How
    1.05
     WHAT
    0.92
    WHAT
    0.92
    what
    0.91
     Why
    0.90
    Why
    0.87
     what
    0.82
    Activations Density 0.194%

    No Known Activations