© 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. 56326
    Prev
    Next
    INDEX
    Explanations

    prepositions and their usage in context

    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
    DoubleQuotes
    -0.54
    principalColumn
    -0.40
    MockBean
    -0.39
     Schmitz
    -0.39
    GTCX
    -0.38
    HasColumnName
    -0.38
     ModelRenderer
    -0.36
     NavController
    -0.36
    providedIn
    -0.33
    œuvre
    -0.33
    POSITIVE LOGITS
     informée
    0.73
     comuniques
    0.58
    endfor
    0.53
    ItemBackground
    0.52
     nakalista
    0.50
    StoreMessageInfo
    0.50
    ginfo
    0.49
     ListTile
    0.49
    Hentet
    0.48
    rungsseite
    0.48
    Activations Density 0.001%

    No Known Activations