© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5989
    Prev
    Next
    INDEX
    Explanations

    terminology related to research methodology and participant classification in studies

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

    Follows "call", "include", "than", or "to"

    np_acts-logits-general · gemini-2.0-flash

    those

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     démocr
    -0.69
    }(),
    -0.69
    MigrationBuilder
    -0.63
     vectorielles
    -0.62
     totul
    -0.61
     sanitaires
    -0.60
     inégal
    -0.56
     ویکی‌پدی
    -0.56
     HasFactory
    -0.55
     الحره
    -0.55
    POSITIVE LOGITS
     those
    2.49
    Those
    2.12
    those
    2.09
     Those
    2.08
     ceux
    1.89
     aquellos
    1.83
     diejenigen
    1.81
     anyone
    1.80
     aqueles
    1.70
     THOSE
    1.69
    Activations Density 1.291%

    No Known Activations