© 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. 90883
    Prev
    Next
    INDEX
    Explanations

    instances of specific coding terminologies and structures within programming-related text

    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
     незавершена
    -0.38
     tejidos
    -0.35
    unistd
    -0.35
    Khi
    -0.34
     ModelExpression
    -0.34
     ši
    -0.33
    ➋
    -0.31
    
    -0.31
    gevens
    -0.31
    :✨
    -0.31
    POSITIVE LOGITS
    jgl
    0.59
    GEBURTSDATUM
    0.56
     CreateTagHelper
    0.52
     RSSSF
    0.52
    Palmarès
    0.51
    NoSuchAlgorithm
    0.47
     dowry
    0.47
    UnknownFieldSet
    0.46
    stdc
    0.46
     OnInit
    0.46
    Activations Density 0.000%

    No Known Activations