© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14977
    Prev
    Next
    INDEX
    Explanations

    references to ethics and approval in research studies

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

    Codes, IDs, serials, and reference numbers

    np_acts-logits-general · gemini-2.0-flash

    codes and numbers

    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
     wireType
    -0.51
    ThroughAttribute
    -0.49
    mietung
    -0.46
     ✭✭
    -0.45
    citos
    -0.44
    setBold
    -0.44
    essura
    -0.43
     morire
    -0.43
    lloworld
    -0.43
    ავ
    -0.42
    POSITIVE LOGITS
     serial
    1.11
     code
    1.10
     number
    1.09
     ID
    1.04
     numbers
    1.03
    number
    1.02
     Serial
    0.96
     identifier
    0.96
    serial
    0.95
     identification
    0.94
    Activations Density 0.503%

    No Known Activations