© 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. 5746
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structural elements in data, particularly focusing on punctuation, variable definitions, and function calls

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

    Appears before parentheses or uncommon punctuation

    np_acts-logits-general · gemini-2.0-flash

    code syntax and symbols

    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
    :✨
    -0.71
     peores
    -0.50
    principalColumn
    -0.48
     ErrIntOverflow
    -0.48
    StoreMessageInfo
    -0.47
     anzu
    -0.46
     normalidad
    -0.46
     desmotivaciones
    -0.46
     kasarigan
    -0.46
    Rüyada
    -0.46
    POSITIVE LOGITS
    uxxxx
    1.04
    .*")]
    0.59
    ("")]
    0.46
    SerializedName
    0.44
    glEnd
    0.42
    rxjs
    0.42
    weightedMode
    0.42
    ="@+
    0.40
     GenerationType
    0.40
    LookAnd
    0.40
    Activations Density 0.416%

    No Known Activations