© 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. 10-GEMMASCOPE-RES-16K
    6. 7613
    Prev
    Next
    INDEX
    Explanations

    instances and contexts of the word "heavy" in relation to various activities or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatelessWidget
    -0.50
     LiveData
    -0.48
    rxjs
    -0.45
    WebControls
    -0.44
    writeField
    -0.44
    CPtr
    -0.44
    jooq
    -0.44
    Rptr
    -0.43
    ionine
    -0.43
    DoesNotExist
    -0.43
    POSITIVE LOGITS
     heavy
    1.99
    Heavy
    1.96
     Heavy
    1.96
    heavy
    1.95
     HEAVY
    1.82
     heaviest
    1.59
     heavier
    1.57
     pesados
    1.30
     pesada
    1.30
     pesado
    1.30
    Activations Density 0.113%

    No Known Activations