© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 12297
    Prev
    Next
    INDEX
    Explanations

    code-related keywords or directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    li
    -0.31
     perang
    -0.28
     tak
    -0.26
    eseorang
    -0.26
     fær
    -0.25
     cũ
    -0.25
     nets
    -0.25
     istruzioni
    -0.25
     персо
    -0.25
     ste
    -0.24
    POSITIVE LOGITS
     propOrder
    0.68
     CreateTagHelper
    0.66
     disambiguazione
    0.65
     الرياضيه
    0.65
    UnusedPrivate
    0.63
    posedge
    0.62
     '\\;'
    0.61
    Попис
    0.61
    inSlope
    0.61
     HttpNotFound
    0.59
    Activations Density 0.000%

    No Known Activations