© 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. 9764
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "has" in various contexts

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

    the verb "has" in sentences describing actions, accomplishments, or state changes.

    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
     يكن
    -0.38
    当时
    -0.38
     be
    -0.38
     счита
    -0.34
    當時
    -0.32
     needing
    -0.31
    Held
    -0.31
    Need
    -0.30
     lack
    -0.30
    PYX
    -0.30
    POSITIVE LOGITS
     begun
    0.75
     commenced
    0.75
    RectangleBorder
    0.69
     arrived
    0.69
     fået
    0.67
    RenderAtEndOf
    0.64
     ब्रेकडाउन
    0.64
     entered
    0.64
    HtmlAttribute
    0.63
    UnusedPrivate
    0.63
    Activations Density 0.397%

    No Known Activations