Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 35653
    Prev
    Next
    INDEX
    Explanations

    opening and closing brackets or braces in programming syntax

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

    public class or method

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     BitmapFactory
    -0.45
    woners
    -0.42
     inspirasi
    -0.42
     goederen
    -0.41
    เธอ
    -0.41
    Бахар
    -0.41
     rijk
    -0.41
     achtergrond
    -0.40
     scherm
    -0.40
     partij
    -0.40
    POSITIVE LOGITS
    migrationBuilder
    0.67
    DockStyle
    0.64
     <<<<<<<<<<<<<<
    0.59
     ExecuteAsync
    0.53
    __':
    0.52
    AxisAlignment
    0.50
    UnitTesting
    0.47
     resourceCulture
    0.47
    KommentareTeilen
    0.47
     indisponible
    0.46
    Activations Density 0.006%

    No Known Activations