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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-131K
    6. 75168
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and their connections within a political context

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

    Sen Tan, Zahid Hamidi

    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
     soos
    -0.38
     Utilisation
    -0.36
     Zwar
    -0.34
     Textile
    -0.33
    ContentAlignment
    -0.33
     Whilst
    -0.32
     utilisation
    -0.32
     noOf
    -0.32
    новништво
    -0.31
     whilst
    -0.31
    POSITIVE LOGITS
    TagMode
    0.69
     utafitiHapana
    0.62
     Italijani
    0.60
     estekak
    0.54
    ſelves
    0.53
    ſelf
    0.51
     houſe
    0.51
     ſtate
    0.50
    FunctionFlags
    0.50
    Personendaten
    0.50
    Activations Density 0.029%

    No Known Activations