© 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. 3111
    Prev
    Next
    INDEX
    Explanations

    geographical features and names related to parks and protected areas

    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
     NZ
    -0.48
     Kiwi
    -0.46
     Ki
    -0.42
    NZ
    -0.39
     Zealand
    -0.37
    Kiwi
    -0.34
     Maori
    -0.33
    nz
    -0.33
     New
    -0.33
    Ki
    -0.33
    POSITIVE LOGITS
     protoimpl
    0.62
     OMITBAD
    0.60
    Tembelea
    0.57
    Попис
    0.57
     Comprometido
    0.56
     ſta
    0.55
     StringTokenizer
    0.54
    resizingMask
    0.54
     PeEnEo
    0.53
     autorytatywna
    0.52
    Activations Density 0.346%

    No Known Activations