© 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. 9-GEMMASCOPE-RES-16K
    6. 9314
    Prev
    Next
    INDEX
    Explanations

    terms related to insect repellent and mosquito prevention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 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
     Infórmanos
    -0.54
     Roskov
    -0.54
     autorytatywna
    -0.52
     estekak
    -0.47
    Билгалдахарш
    -0.44
    Cyfeiriadau
    -0.42
     Ajust
    -0.42
    IntoConstraints
    -0.41
    TypedDataSet
    -0.41
     AutoMapper
    -0.41
    POSITIVE LOGITS
     repel
    0.82
     repulsion
    0.72
     repellent
    0.72
     repelled
    0.71
     ward
    0.59
     repul
    0.56
     scare
    0.54
     dissu
    0.52
     dispel
    0.52
     deflect
    0.51
    Activations Density 0.243%

    No Known Activations