© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 598
    Prev
    Next
    INDEX
    Explanations

    references to touch or tactile interactions

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

    the word "touch" or "TOUCH" in various contexts.

    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
    gezogen
    -0.30
     vapeur
    -0.29
     mesmas
    -0.29
    neté
    -0.28
     tiroirs
    -0.28
    où
    -0.27
    RTSN
    -0.27
     boletín
    -0.27
     rağmen
    -0.26
     ventilación
    -0.26
    POSITIVE LOGITS
     Touch
    1.06
    touch
    1.00
    Touch
    0.99
     touch
    0.99
     TOUCH
    0.97
    TOUCH
    0.94
     touches
    0.86
     touched
    0.84
    touches
    0.80
    touched
    0.80
    Activations Density 0.118%

    No Known Activations