Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 5269
    Prev
    Next
    INDEX
    Explanations

    references to large quantities or scales

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     small
    -0.73
     large
    -0.72
     kleines
    -0.70
     pequeno
    -0.68
    tiny
    -0.68
     небольшой
    -0.67
     pequeñas
    -0.67
    large
    -0.67
     pequenas
    -0.66
     smaller
    -0.66
    POSITIVE LOGITS
     scale
    0.99
     amounts
    0.97
     quantities
    0.90
     amount
    0.82
    scale
    0.81
    mouth
    0.78
     numbers
    0.76
    ConstraintMaker
    0.74
     Scale
    0.74
    amounts
    0.73
    Activations Density 0.398%

    No Known Activations