© 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. 1307
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to coding and programming

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

    HTML or code-related tags

    np_acts-logits-general · gemini-2.0-flash

    website file paths

    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
    MigrationBuilder
    -0.81
     AssemblyProduct
    -0.74
     typelib
    -0.72
    queryInterface
    -0.70
    +:+
    -0.69
     resourceCulture
    -0.66
    invokeLater
    -0.64
    ⟬
    -0.64
    Tembelea
    -0.63
     AssemblyVersion
    -0.61
    POSITIVE LOGITS
    SourceChecksum
    1.17
    TagHelper
    0.76
    ScopeManager
    0.73
    fjspx
    0.71
    ValueStyle
    0.56
    Kaynakça
    0.46
    Razor
    0.45
    TagHelpers
    0.44
    cshtml
    0.39
    stücks
    0.39
    Activations Density 0.008%

    No Known Activations