© 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. 21186
    Prev
    Next
    INDEX
    Explanations

    specific annotations and references to research papers or citations in academic writing

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

    citations and code snippets

    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
    脚注の使い方
    -0.79
    IntoConstraints
    -0.73
    findpost
    -0.71
     queſta
    -0.69
     getItemCount
    -0.69
     nakalista
    -0.68
     MainAxisSize
    -0.67
    Vidite
    -0.65
    HasAnnotation
    -0.65
    featureID
    -0.64
    POSITIVE LOGITS
     '
    0.39
     «
    0.35
     F
    0.33
     ‘
    0.32
     Wid
    0.32
     بیم
    0.32
    ®
    0.32
     Em
    0.31
    ),
    0.30
    『
    0.30
    Activations Density 0.111%

    No Known Activations