© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104687
    Prev
    Next
    INDEX
    Explanations

    strings or JSON-like structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     المعيارى
    -0.80
     HttpNotFound
    -0.73
     Chwiliwch
    -0.70
    SharedDtor
    -0.69
     Photocase
    -0.69
     propOrder
    -0.69
     kasarigan
    -0.68
     مرئيه
    -0.68
     increí
    -0.67
    Aholisi
    -0.66
    POSITIVE LOGITS
    /***/
    0.43
     came
    0.28
    Click
    0.26
     yesterday
    0.25
    Yesterday
    0.25
    AttributeName
    0.25
     SPDX
    0.25
    omes
    0.24
     editorial
    0.24
    </blockquote>
    0.23
    Activations Density 0.003%

    No Known Activations