© 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. 9-GEMMASCOPE-RES-131K
    11. 107538
    Prev
    Next
    INDEX
    Explanations

    occurrences of coding library import statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnimationsModule
    -0.56
    -------
    -0.48
    Kanpo
    -0.48
     prisa
    -0.48
    EFIAPI
    -0.47
     orgánico
    -0.47
     japonés
    -0.47
     aislado
    -0.46
    IBOutlet
    -0.46
     inmediato
    -0.46
    POSITIVE LOGITS
    __":
    0.51
    arach
    0.46
    ombe
    0.46
     clen
    0.45
     queſta
    0.44
     мәкал
    0.44
    BibitemShut
    0.44
    umeur
    0.43
     TIC
    0.43
     CCM
    0.42
    Activations Density 0.002%

    No Known Activations