© 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. 3-GEMMASCOPE-RES-16K
    6. 15995
    Prev
    Next
    INDEX
    Explanations

    instances of the word "grab" in various grammatical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.69
     onPostExecute
    -0.63
    níku
    -0.62
    )`
    -0.60
    థ
    -0.60
     tố
    -0.60
    setPassword
    -0.60
    </strong>
    -0.58
    ποτε
    -0.58
    erty
    -0.57
    POSITIVE LOGITS
     grab
    2.98
     grabs
    2.81
     Grab
    2.77
    grab
    2.73
    Grab
    2.70
     grabbing
    2.67
     grabbed
    2.64
     snatch
    1.69
     snatched
    1.48
     seize
    1.36
    Activations Density 0.028%

    No Known Activations