© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1368
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and operations

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

    Calculations with negative numbers

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and code

    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
     practically
    -0.36
    retudo
    -0.36
     seemingly
    -0.35
    ArrowToggle
    -0.35
    DockStyle
    -0.35
     virtually
    -0.34
    ználat
    -0.33
     Virtually
    -0.33
     contextLoads
    -0.32
    也非常
    -0.32
    POSITIVE LOGITS
    addContainerGap
    0.67
    Hochspringen
    0.56
    SpringRunner
    0.54
    aarrggbb
    0.54
    Swatch
    0.52
    VersionUID
    0.50
    InlineData
    0.50
    iteracy
    0.50
     HasFactory
    0.50
    ConverterFactory
    0.49
    Activations Density 0.314%

    No Known Activations