© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 589
    Prev
    Next
    INDEX
    Explanations

    various contexts of the word "search" and its related forms

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

    "search" or related terms

    np_acts-logits-general · gemini-2.0-flash

    search on or followed by preposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     companyId
    -0.66
     createdBy
    -0.64
     clientId
    -0.63
    fromCharCode
    -0.63
     itemId
    -0.60
     defStyleAttr
    -0.60
    getFullYear
    -0.59
     newVal
    -0.58
     HTMLElement
    -0.58
     BaseModel
    -0.57
    POSITIVE LOGITS
     search
    1.31
     Search
    1.23
    search
    1.17
    Search
    1.14
     SEARCH
    1.06
    SEARCH
    0.95
    setSearch
    0.93
    onSearch
    0.90
     searching
    0.87
    searching
    0.85
    Activations Density 0.087%

    No Known Activations