© 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
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 1304
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.71
    ghalaya
    -0.65
    :✨
    -0.62
    Afrika
    -0.60
     Ghanaian
    -0.60
    Israeli
    -0.60
     Malaysian
    -0.59
     AMERICAN
    -0.59
     nahilalakip
    -0.59
    Canadian
    -0.59
    POSITIVE LOGITS
    ecore
    0.40
     milik
    0.38
     onOptions
    0.37
     zowel
    0.37
    onAttach
    0.36
     tė
    0.34
     końca
    0.34
     řek
    0.33
     schönsten
    0.33
    jelasan
    0.32
    Activations Density 0.415%

    No Known Activations