© 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. 25-GEMMASCOPE-RES-16K
    6. 15390
    Prev
    Next
    INDEX
    Explanations

    references to laboratory results and measurements in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     canlynol
    -0.48
    ?,?,
    -0.41
    ᚐ
    -0.36
    </caption>
    -0.35
    Folgende
    -0.35
     isNameExpr
    -0.35
    Архівовано
    -0.34
     detailsNormal
    -0.34
     Paglinawan
    -0.34
     AssemblyCompany
    -0.34
    POSITIVE LOGITS
     Vikipedi
    0.53
    cheur
    0.47
     Marav
    0.46
    CascadeType
    0.42
     Zing
    0.41
     Jap
    0.41
    хьтан
    0.41
    numerusform
    0.41
    RegisterType
    0.40
    ->__
    0.39
    Activations Density 0.572%

    No Known Activations