Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 613
    Prev
    Next
    INDEX
    Explanations

    names of places or geographical locations

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

    place names and county divisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.58
     GenerationType
    -0.57
    +:+
    -0.52
    Попис
    -0.52
    argout
    -0.52
    parsedMessage
    -0.52
    Personensuche
    -0.51
    ftagPool
    -0.50
     MediatR
    -0.49
     surla
    -0.48
    POSITIVE LOGITS
     sep
    0.40
     pinulongan
    0.39
     acc
    0.39
     propOrder
    0.37
    身边的
    0.36
     INT
    0.35
     goc
    0.35
     Joplin
    0.34
    Tas
    0.33
     SwiftUI
    0.33
    Activations Density 0.039%

    No Known Activations