© 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. 107466
    Prev
    Next
    INDEX
    Explanations

    references to "column" or similar terms associated with data organization

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

    column or columns

    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
     menging
    -0.44
     nổ
    -0.44
    ade
    -0.42
    fresh
    -0.42
     yarar
    -0.41
    afety
    -0.41
     ​​
    -0.40
     Sicherheits
    -0.40
    SAFETY
    -0.39
     freshest
    -0.39
    POSITIVE LOGITS
     Column
    1.31
    Column
    1.29
     column
    1.27
    column
    1.15
     getColumn
    1.10
     Columns
    1.09
     TableColumn
    1.08
     COLUMN
    1.06
     columns
    1.04
    COLUMN
    0.99
    Activations Density 0.015%

    No Known Activations