© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 55155
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "select" and variations of it in different contexts

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

    select

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Données
    -0.55
     createdBy
    -0.54
    ian
    -0.54
     Huns
    -0.52
    ized
    -0.50
     Iden
    -0.50
     itemId
    -0.49
     currentNode
    -0.49
     Karsten
    -0.49
    Srv
    -0.48
    POSITIVE LOGITS
    select
    1.04
    Select
    0.87
     Select
    0.84
     SELECT
    0.84
     select
    0.82
    SELECT
    0.81
     Seleccione
    0.66
    SelectAll
    0.57
     Sélectionnez
    0.57
     selects
    0.56
    Activations Density 0.013%

    No Known Activations