© 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. 1717
    Prev
    Next
    INDEX
    Explanations

    sections of code or annotations related to software documentation and metadata

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

    Code or comments in various programming languages

    np_acts-logits-general · gemini-2.0-flash

    code comments and separators

    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
    出版年
    -1.08
    EndInit
    -0.77
    PerformLayout
    -0.75
    ReusableCell
    -0.75
    IsContent
    -0.74
     utafitiHapana
    -0.71
    findpost
    -0.70
    Viitteet
    -0.68
    OGND
    -0.65
    errHandler
    -0.64
    POSITIVE LOGITS
    Diweddarwch
    0.53
    ufficio
    0.46
    TableAdapter
    0.46
     Lider
    0.45
     recens
    0.43
     banks
    0.43
    yargs
    0.43
    benefit
    0.42
     ammon
    0.42
     Minor
    0.42
    Activations Density 0.099%

    No Known Activations