© 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. 23-GEMMASCOPE-RES-16K
    11. 2084
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their usage in expressing opinions or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.64
    MigrationBuilder
    -0.57
     GTK
    -0.52
    tvguidetime
    -0.49
    GTK
    -0.49
    CompilerServices
    -0.49
    voltaic
    -0.49
    ChildScrollView
    -0.49
     Wiktionnaire
    -0.48
     GenerationType
    -0.48
    POSITIVE LOGITS
     نے
    0.44
     Untersch
    0.35
     Kreise
    0.35
    vezető
    0.35
     libremente
    0.34
     Verbrechen
    0.34
    zelf
    0.34
    tagext
    0.34
     cárcel
    0.32
     Exacts
    0.32
    Activations Density 0.062%

    No Known Activations