© 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. 4342
    Prev
    Next
    INDEX
    Explanations

    alphanumeric characters and letters structured in a format resembling list items or sections in a document

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

    Tokens that precede a parenthetical close

    np_acts-logits-general · gemini-2.0-flash

    enumerated lists with closing parenthesis

    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
    tonsoft
    -0.64
    mayr
    -0.55
    (&:
    -0.52
    >",
    -0.51
    िया
    -0.51
    a
    -0.51
     endfor
    -0.51
     المعيارى
    -0.51
    quelize
    -0.50
    __":
    -0.50
    POSITIVE LOGITS
    istoitu
    0.65
    VIAF
    0.62
     ***!
    0.57
    enance
    0.54
    WEBPACK
    0.54
     createSlice
    0.54
    neſs
    0.53
    ……"
    0.49
    ISupport
    0.49
    SafeMath
    0.49
    Activations Density 0.162%

    No Known Activations