© 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. 8443
    Prev
    Next
    INDEX
    Explanations

    instances of physical contact or actions involving grabbing and holding

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

    physical contact between people, particularly grasping or holding someone's body part.

    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
    ViewFeatures
    -0.47
    叠
    -0.35
     PD
    -0.34
     systematic
    -0.34
     Padova
    -0.34
     המא
    -0.34
    itemBuilder
    -0.33
    疊
    -0.33
    jednoc
    -0.32
     Mir
    -0.31
    POSITIVE LOGITS
     hold
    1.18
     grip
    1.08
     holding
    1.06
     Hold
    1.02
     holds
    0.99
     HOLD
    0.98
     grasping
    0.98
    Hold
    0.97
    grab
    0.94
     Holding
    0.94
    Activations Density 0.150%

    No Known Activations