© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 7992
    Prev
    Next
    INDEX
    Explanations

    patterns related to biological sequences or identifiers, particularly in genetic or proteomic data

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

    Two-letter sequence followed by specific letters

    np_acts-logits-general · gemini-2.0-flash

    CA, BA, RA, TA, MAR beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
    T
    -0.82
    D
    -0.70
    TTE
    -0.61
    TG
    -0.59
     Chwiliwch
    -0.59
    TERS
    -0.56
    S
    -0.56
    TN
    -0.55
    TED
    -0.55
    adalajara
    -0.55
    POSITIVE LOGITS
    t
    0.48
    O
    0.43
    tine
    0.43
    m
    0.41
    tch
    0.41
    Outro
    0.40
    ּ
    0.40
    rm
    0.40
    Ƚ
    0.40
    tin
    0.40
    Activations Density 0.461%

    No Known Activations