© 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. 13962
    Prev
    Next
    INDEX
    Explanations

    HTML form elements and attributes

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

    Text fragments after commas or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    a, name, childhood

    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
    с
    -0.45
     Touchable
    -0.42
     "<
    -0.42
    f
    -0.42
    <
    -0.42
    ्या
    -0.41
    ele
    -0.41
     teles
    -0.40
    Tar
    -0.40
    sty
    -0.39
    POSITIVE LOGITS
     ModelExpression
    0.84
    adə
    0.77
     insuffisamment
    0.74
    esModule
    0.74
    InjectAttribute
    0.73
    WEBPACK
    0.72
    Hauptartikel
    0.72
     Савезне
    0.72
    WebControls
    0.71
    requireNonNull
    0.71
    Activations Density 0.023%

    No Known Activations