© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 387
    Prev
    Next
    INDEX
    Explanations

    references to hands and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "hand" and related body parts

    np_acts-logits-general · gemini-2.0-flash

    hands on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stör
    -0.37
     Brenn
    -0.35
     vinagre
    -0.35
     nocturno
    -0.35
    场所
    -0.34
     vinegar
    -0.34
     imageNamed
    -0.34
    脚注の使い方
    -0.34
     Cuerpo
    -0.33
    一头
    -0.33
    POSITIVE LOGITS
    Hands
    1.02
     Hands
    1.02
     hand
    0.99
     Hand
    0.97
    Hand
    0.96
    hands
    0.95
     hands
    0.93
     HANDS
    0.92
     fingers
    0.91
    finger
    0.85
    Activations Density 0.400%

    No Known Activations