© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1728
    Prev
    Next
    INDEX
    Explanations

    actions related to physically seizing or holding something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    বহ
    -0.60
    níku
    -0.58
     onPostExecute
    -0.58
     образом
    -0.58
     Münch
    -0.58
    lowe
    -0.57
    Hoje
    -0.56
     Stillwater
    -0.56
    rowad
    -0.56
    Arco
    -0.55
    POSITIVE LOGITS
     grab
    1.50
     grabs
    1.50
     grabbed
    1.44
     Grab
    1.37
     grabbing
    1.36
    Grab
    1.30
    grab
    1.28
     grip
    1.23
     grasping
    1.22
     grasp
    1.21
    Activations Density 0.104%

    No Known Activations