© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10231
    Prev
    Next
    INDEX
    Explanations

    references to other people, entities, or items in a context that indicates comparison or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    outSlope
    -0.50
    TagMode
    -0.49
     ProtoMessage
    -0.48
     ujednoznacz
    -0.47
    guiente
    -0.45
     sebou
    -0.44
    MemoryWarning
    -0.44
    providedIn
    -0.44
     richieste
    -0.43
     dictadura
    -0.42
    POSITIVE LOGITS
     Etc
    0.70
    Etc
    0.69
    等
    0.66
     ETC
    0.65
     등
    0.65
     etc
    0.65
     等
    0.63
    などの
    0.61
    etc
    0.60
    ETC
    0.59
    Activations Density 0.146%

    No Known Activations