© 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. 18-GEMMASCOPE-RES-16K
    11. 13768
    Prev
    Next
    INDEX
    Explanations

    code or syntax structures related to programming and data format specifications

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

    Mathematical or algebraic notation

    np_acts-logits-general · gemini-2.0-flash

    punctuation and other symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nauki
    -0.53
     --
    -0.46
    posedge
    -0.46
     ((((
    -0.45
    "
    -0.45
     (
    -0.45
     ter
    -0.44
    nien
    -0.44
    Similarly
    -0.44
    ”
    -0.43
    POSITIVE LOGITS
    elemField
    0.98
    yntaxException
    0.89
    Còn
    0.85
     myſelf
    0.81
     itſelf
    0.81
    Cordialement
    0.78
     Efq
    0.73
    tagHelperRunner
    0.71
    IVEREF
    0.71
    IntoConstraints
    0.70
    Activations Density 0.473%

    No Known Activations