© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 44300
    Prev
    Next
    INDEX
    Explanations

    occurrences of structured data related to programming, such as file types, source code organization, and configuration files

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

    file suffixes and versions

    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
     للمعارف
    -0.67
    Javadoc
    -0.51
    >{@
    -0.47
     "..\..\
    -0.46
    IntoConstraints
    -0.46
     فريبيس
    -0.46
    脚注の使い方
    -0.46
     JpaRepository
    -0.45
    IBOutlet
    -0.44
     FetchType
    -0.44
    POSITIVE LOGITS
    orig
    0.43
    ORIG
    0.41
     backup
    0.40
    hiana
    0.37
     副本
    0.37
     Vort
    0.37
    bak
    0.36
    Unavailable
    0.36
     backups
    0.35
    的后
    0.35
    Activations Density 0.148%

    No Known Activations