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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 754
    Prev
    Next
    INDEX
    Explanations

    discussions around body language and gestures in social interactions

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

    Actions, movements, techniques, and gestures

    np_acts-logits-general · gemini-2.0-flash

    physical actions and techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    responseData
    -0.41
    /******/
    -0.39
     markets
    -0.39
     rodzin
    -0.38
     beneficiaries
    -0.37
    httphttps
    -0.36
    ']);
    
    -0.36
     שוליים
    -0.36
     charges
    -0.36
    LikeLike
    -0.35
    POSITIVE LOGITS
     technique
    0.68
    technique
    0.59
     Technique
    0.58
     TECHNIQUE
    0.57
     posture
    0.54
     techniques
    0.53
    teknik
    0.52
     gesture
    0.52
     gestures
    0.51
    Technique
    0.51
    Activations Density 0.338%

    No Known Activations