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. 41-GEMMASCOPE-RES-16K
    6. 7399
    Prev
    Next
    INDEX
    Explanations

    important names and entities related to events and accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.44
    الحياه
    -0.38
    toHave
    -0.37
    protoc
    -0.36
    ocyan
    -0.35
    reportWebVitals
    -0.34
    InputBorder
    -0.33
    wapV
    -0.33
    cali
    -0.33
    lccn
    -0.33
    POSITIVE LOGITS
     cas
    3.16
     Cas
    3.09
    Cas
    3.00
     CAS
    2.63
     Kas
    2.56
     kas
    2.52
    cas
    2.50
    Kas
    2.36
     Cass
    2.36
    CAS
    2.31
    Activations Density 1.325%

    No Known Activations