© 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. 108031
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and code-related syntax elements

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

    coordinates and separators

    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
    Véase
    -0.28
     TAMBIÉN
    -0.26
     longest
    -0.26
    年生
    -0.25
    Longest
    -0.25
     elim
    -0.25
    PMailer
    -0.24
    优秀
    -0.23
     exercí
    -0.22
     popol
    -0.22
    POSITIVE LOGITS
    ellido
    0.68
    sidemargin
    0.60
    ViewImports
    0.59
    extAlignment
    0.58
    rosine
    0.56
     GenerationType
    0.56
    CardContent
    0.56
    хьтан
    0.56
     Waſſer
    0.56
    XmlAccessorType
    0.55
    Activations Density 0.039%

    No Known Activations