© 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. 12754
    Prev
    Next
    INDEX
    Explanations

    phrases related to notable global locations and their characteristics

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

    countries and their famous traits

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    baguna
    -0.34
    èdent
    -0.33
     acep
    -0.33
    SharedDtor
    -0.32
     Crum
    -0.32
     CÁ
    -0.32
    jspb
    -0.31
     denuncia
    -0.30
     prohibido
    -0.30
    Geplaatst
    -0.29
    POSITIVE LOGITS
    AnimationsModule
    0.61
    pulseira
    0.51
    VINCE
    0.49
    parsedMessage
    0.48
     Lightboxes
    0.48
    LEncoder
    0.48
     küpe
    0.47
    enterOuterAlt
    0.47
     NavController
    0.46
    NOPQRST
    0.46
    Activations Density 0.118%

    No Known Activations