© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 23301
    Prev
    Next
    INDEX
    Explanations

    specific numerical references, possibly related to software versions or identification codes

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

    Chham Cyfeiriadau

    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
     algún
    -0.34
     geladeira
    -0.34
     próprias
    -0.31
     Turm
    -0.31
     propias
    -0.31
     Meksi
    -0.31
     Fø
    -0.31
    Serviço
    -0.31
     Hukum
    -0.30
     Glied
    -0.30
    POSITIVE LOGITS
    ScopeManager
    0.82
    parsedMessage
    0.80
    RTEX
    0.79
    DockStyle
    0.73
     nakalista
    0.73
    principalTable
    0.70
    RTSN
    0.68
    MessageState
    0.66
    Chham
    0.66
    Cyfeiriadau
    0.63
    Activations Density 0.004%

    No Known Activations