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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 77065
    Prev
    Next
    INDEX
    Explanations

    references to fingers

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

    fingers crossed or around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     world
    -0.37
     Alb
    -0.37
     proclamation
    -0.36
    impianto
    -0.36
     Wake
    -0.34
     wheel
    -0.34
    Wake
    -0.33
     venue
    -0.33
     макия
    -0.33
    jestic
    -0.32
    POSITIVE LOGITS
     fingers
    1.95
    fingers
    1.80
     Fingers
    1.78
    Fingers
    1.75
     doigts
    1.16
     dedos
    1.10
     fingertips
    1.05
    手指
    0.84
    Hands
    0.80
     Händen
    0.78
    Activations Density 0.005%

    No Known Activations