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. 102444
    Prev
    Next
    INDEX
    Explanations

    sentences that convey location or place descriptions

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

    city and town locations

    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
     ASSOCIATED
    -0.41
    ModelAttribute
    -0.41
    minimum
    -0.39
    pido
    -0.38
     ASSOCIATES
    -0.37
     CONSE
    -0.36
    amzn
    -0.36
    üedad
    -0.35
     Sociales
    -0.35
     Stiftung
    -0.34
    POSITIVE LOGITS
     town
    0.84
     city
    0.82
     cities
    0.81
     getCity
    0.78
     ciudades
    0.76
     ciudad
    0.75
    เมือง
    0.74
     cidades
    0.73
     towns
    0.72
     città
    0.70
    Activations Density 0.061%

    No Known Activations