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. 108627
    Prev
    Next
    INDEX
    Explanations

    names of specific locations and brands

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

    names and places

    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
     hende
    -0.33
    hawatir
    -0.32
     cappuccio
    -0.30
    判
    -0.28
    SpringBootTest
    -0.28
     mattino
    -0.27
    rze
    -0.27
     Estadual
    -0.27
    ")){
    
    -0.27
    ashqai
    -0.27
    POSITIVE LOGITS
    endpush
    0.72
     Infórmanos
    0.71
     estekak
    0.66
    Legends
    0.63
     Legends
    0.61
     nahilalakip
    0.60
    ViewFeatures
    0.59
     Theſe
    0.59
     sliders
    0.59
    +#+#
    0.57
    Activations Density 0.040%

    No Known Activations