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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15615
    Prev
    Next
    INDEX
    Explanations

    punctuation and quotation marks related to speech and thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextAppearance
    -0.48
     utafitiHapana
    -0.46
    arbeiter
    -0.41
     Vann
    -0.41
    CppMethod
    -0.40
    ंदीखरीदारी
    -0.40
    edoc
    -0.39
    jęt
    -0.39
    tokine
    -0.39
     Ikan
    -0.37
    POSITIVE LOGITS
    printStackTrace
    0.47
     [/
    0.47
    requently
    0.47
     GIPHY
    0.46
     sâ
    0.46
     Wakefield
    0.45
    [/
    0.45
     Â
    0.45
     Norwood
    0.44
     Christy
    0.44
    Activations Density 0.318%

    No Known Activations