© 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. 20-GEMMASCOPE-RES-16K
    11. 6873
    Prev
    Next
    INDEX
    Explanations

    the initial markers or indicators of a document, such as a start token

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

    Code, programming, or special characters

    np_acts-logits-general · gemini-2.0-flash

    special characters and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "):
    -0.49
    כח
    -0.48
     Land
    -0.48
    =[]
    -0.48
    ProductCategory
    -0.47
    ":
    -0.47
    PostId
    -0.46
    =[];
    -0.45
    CategoryId
    -0.45
    RoleId
    -0.45
    POSITIVE LOGITS
    $_['
    0.98
    IsContent
    0.94
    +#+#
    0.89
    MigrationBuilder
    0.84
    SourceChecksum
    0.83
    GEBURTSDATUM
    0.82
     Référence
    0.82
    Geplaatst
    0.81
    bitField
    0.78
     оригіналу
    0.76
    Activations Density 0.095%

    No Known Activations