© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5728
    Prev
    Next
    INDEX
    Explanations

    instances of the word "search" and related terms indicating querying or searching actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    whom
    -0.49
    pod
    -0.48
     createdBy
    -0.47
    accompag
    -0.46
     clientId
    -0.45
     postData
    -0.43
     BaseModel
    -0.43
     accessToken
    -0.43
    Condol
    -0.43
    getFullYear
    -0.42
    POSITIVE LOGITS
     search
    1.99
     Search
    1.78
    search
    1.67
     SEARCH
    1.66
    Search
    1.63
    SEARCH
    1.47
     searches
    1.43
     searching
    1.40
     searched
    1.40
     Searching
    1.31
    Activations Density 0.104%

    No Known Activations