© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58560
    Prev
    Next
    INDEX
    Explanations

    keywords and concepts related to programming operators

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

    operators and interactions

    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
    EndGlobalSection
    -0.74
    RTCK
    -0.72
    ########.
    -0.69
    ISupport
    -0.67
    الحياه
    -0.65
    دانشنامهٔ
    -0.64
    bildtitel
    -0.62
     للاسماء
    -0.62
    <unused1>
    -0.61
     Menſchen
    -0.61
    POSITIVE LOGITS
     between
    0.28
    LabelTagHelper
    0.27
    CloseOperation
    0.27
    prefixer
    0.27
     zwischen
    0.27
    CrossRef
    0.25
     surrounded
    0.25
     defaultstate
    0.25
     mat
    0.24
    Asts
    0.24
    Activations Density 0.008%

    No Known Activations