© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 217
    Prev
    Next
    INDEX
    Explanations

    locations and administrative divisions in Japan, particularly Osaka

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

    japanese cities and institutions

    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
    ThroughAttribute
    -0.43
     Try
    -0.40
    Try
    -0.37
    HMIS
    -0.35
     acrí
    -0.34
    __).
    -0.34
    JoinTable
    -0.33
     surla
    -0.33
    IID
    -0.33
    sträger
    -0.33
    POSITIVE LOGITS
     Osaka
    2.41
    Osaka
    2.16
    大阪
    1.28
     大阪
    1.16
     Nagoya
    0.78
     Kans
    0.71
    大阪府
    0.69
     OSA
    0.68
     Japan
    0.65
     Fukuoka
    0.65
    Activations Density 0.003%

    No Known Activations