© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4253
    Prev
    Next
    INDEX
    Explanations

    commands and functions in programming, particularly those related to data manipulation and generation

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

    programming-related terms and code elements, especially those referring to functions, processes, actions, or methods in technical or coding contexts.

    oai_token-act-pair · gpt-4.1-2025-04-14Triggered by @ywhp2c8tjm

    words and code snippets relating to computer programming.

    oai_token-act-pair · gemini-2.0-flashTriggered by @ywhp2c8tjm

    before "Mail" or "Mails"

    np_acts-logits-general · gemini-2.0-flash

    commands and operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    ResponseWriter
    -0.44
    middlewares
    -0.42
    CppMethod
    -0.40
    migrationBuilder
    -0.38
     megfe
    -0.37
    コンテンツ
    -0.37
     *++
    -0.35
    bcryptjs
    -0.35
    мін
    -0.35
    それでも
    -0.35
    POSITIVE LOGITS
    ьажоргаш
    0.64
    EnableWeb
    0.54
    tagHelperRunner
    0.53
     pinulongan
    0.51
     automático
    0.51
    })*/
    0.51
     barato
    0.50
    Vegeu
    0.49
     Locate
    0.49
     mecánico
    0.48
    Activations Density 0.679%

    No Known Activations