© 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. 56321
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax elements related to data structures and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    parsedMessage
    -0.57
    WriteTagHelper
    -0.55
    bufio
    -0.54
    deth
    -0.53
    onomía
    -0.53
     esternos
    -0.53
    Personendaten
    -0.53
     فريبيس
    -0.52
     &___
    -0.50
    semantics
    -0.49
    POSITIVE LOGITS
    +#+#
    0.47
     Roskov
    0.43
     Hentet
    0.36
     flotante
    0.36
     Existenz
    0.35
     oublier
    0.34
    pozdrawiam
    0.33
    endregion
    0.33
     préférence
    0.33
     SEDS
    0.33
    Activations Density 0.112%

    No Known Activations