© 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. 31-GEMMASCOPE-RES-131K
    11. 21261
    Prev
    Next
    INDEX
    Explanations

    structural elements and attributes related to markup languages or programming frameworks

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

    description, summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.71
    ↹
    -0.65
    EndContext
    -0.64
     disambiguazione
    -0.63
    AndEndTag
    -0.62
    хьтан
    -0.62
    󠁿
    -0.61
    __(/*!
    -0.59
    msgTypes
    -0.59
    ValueStyle
    -0.57
    POSITIVE LOGITS
     description
    1.09
     Description
    0.98
    description
    0.89
    Description
    0.87
     descriptions
    0.83
     details
    0.82
     Beschreibung
    0.76
     DESCRIPTION
    0.75
     overview
    0.73
     detailed
    0.71
    Activations Density 0.014%

    No Known Activations