© 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. 82672
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods and slashes

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

    android activity and ui elements

    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
     juſ
    -0.59
     pouvoit
    -0.50
    autant
    -0.47
     auroit
    -0.47
     feroit
    -0.46
     avoient
    -0.45
     juſt
    -0.45
     deſt
    -0.44
     exécu
    -0.44
     neceſſ
    -0.43
    POSITIVE LOGITS
     ['./
    0.68
    __(/*!
    0.67
     незавершена
    0.63
    ::_('
    0.62
    ⤹
    0.61
     Administrativna
    0.60
    __*/
    0.59
    دانشنامهٔ
    0.58
     مرئيه
    0.56
    (&:
    0.56
    Activations Density 0.008%

    No Known Activations