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

    Neuronpedia

    APICircuit 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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3623
    Prev
    Next
    INDEX
    Explanations

    geographical and locational references related to Alaska

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    UseVisualStyle
    -0.44
    vinilo
    -0.39
    querySelector
    -0.37
    posedge
    -0.37
    @[+][
    -0.35
    niająca
    -0.35
    verifyException
    -0.34
    ategy
    -0.34
     humain
    -0.33
     genomen
    -0.33
    POSITIVE LOGITS
     Alaska
    1.02
    Alaska
    0.97
     Alaskan
    0.89
     alaska
    0.89
     Anchorage
    0.81
    wahati
    0.69
    alaska
    0.60
     Juneau
    0.57
     Hokkaido
    0.55
     北海道
    0.52
    Activations Density 0.141%

    No Known Activations