© 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. 24-GEMMASCOPE-RES-16K
    11. 488
    Prev
    Next
    INDEX
    Explanations

    actions related to creation, implementation, and recognition within various contexts

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

    followed by prepositions/punctuation

    np_acts-logits-general · gemini-2.0-flash

    verbs preceding punctuation or prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.63
    esModule
    -0.45
     remo
    -0.45
     wan
    -0.44
     dagger
    -0.43
     idem
    -0.43
     Lordship
    -0.43
     damper
    -0.42
    PropertyChanging
    -0.42
    figsize
    -0.42
    POSITIVE LOGITS
     serpiente
    0.46
     cálido
    0.45
     propuesto
    0.44
     vosotros
    0.44
    EDEFAULT
    0.44
     gantung
    0.44
     Descub
    0.43
    verifyException
    0.43
    endpush
    0.42
    går
    0.42
    Activations Density 0.323%

    No Known Activations