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. 81382
    Prev
    Next
    INDEX
    Explanations

    references to various agencies

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

    agency names

    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
    GHI
    -0.57
     TBC
    -0.48
    Wim
    -0.45
     JK
    -0.45
    TBC
    -0.44
     SOT
    -0.44
     LV
    -0.43
    LUT
    -0.43
     Rot
    -0.43
     LIS
    -0.43
    POSITIVE LOGITS
     Agency
    2.05
    Agency
    1.73
     AGENCY
    1.57
     Agencies
    1.12
     Agencia
    1.11
    agency
    1.06
    Agence
    1.04
     Agen
    1.01
     agency
    0.99
     Agence
    0.92
    Activations Density 0.002%

    No Known Activations