© 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. 31-GEMMASCOPE-RES-16K
    6. 4735
    Prev
    Next
    INDEX
    Explanations

    words related to hands and their functions

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

    the phrase "hand-" or "hand" followed by a hyphen or specific words that form compound terms beginning with "hand".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.48
    expliquer
    -0.38
     poesia
    -0.37
    Kjelder
    -0.35
     tajam
    -0.34
    cillo
    -0.34
     poeta
    -0.34
    TemporalType
    -0.34
     conducta
    -0.33
    ፩
    -0.33
    POSITIVE LOGITS
     Hand
    1.02
    Hand
    1.01
     hand
    0.86
     HAND
    0.84
    HAND
    0.77
    hand
    0.75
    maiden
    0.72
    ✋
    0.67
     hånd
    0.65
    Handshake
    0.62
    Activations Density 0.060%

    No Known Activations