© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2782
    Prev
    Next
    INDEX
    Explanations

    verbs and modal verbs, especially in relation to theoretical or hypothetical situations

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

    German modal verbs and auxiliary verbs in complex verb constructions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    quelize
    -0.47
    providedIn
    -0.47
    tagHelperRunner
    -0.46
    näm
    -0.45
    ConstraintMaker
    -0.45
    Бахар
    -0.43
     ſind
    -0.42
     détaillés
    -0.42
     StringTokenizer
    -0.41
     nôtre
    -0.41
    POSITIVE LOGITS
     into
    0.76
     onto
    0.58
    into
    0.56
     Into
    0.54
     einen
    0.52
     את
    0.52
    Into
    0.52
    einen
    0.50
     in
    0.47
     INTO
    0.47
    Activations Density 0.037%

    No Known Activations