© 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. 18-GEMMASCOPE-RES-16K
    11. 929
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and related formatting characters

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

    Code or markup attributes starting with quotation marks

    np_acts-logits-general · gemini-2.0-flash

    quotations and delimiters

    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
    tieth
    -0.53
    englisch
    -0.52
    theless
    -0.52
     espirituales
    -0.49
    netty
    -0.49
    vastava
    -0.48
    HasIndex
    -0.48
    页面存档备份
    -0.48
    ViewImports
    -0.47
    FlatList
    -0.47
    POSITIVE LOGITS
    '"
    0.98
     propOrder
    0.81
    Manbalar
    0.79
    ukunfts
    0.73
    (@"
    0.71
    Abitanti
    0.71
    __*/
    0.70
    Geplaatst
    0.69
    interopRequire
    0.69
     LSM
    0.69
    Activations Density 0.404%

    No Known Activations