© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12646
    Prev
    Next
    INDEX
    Explanations

    nodes and connections in complex structures or processes

    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
    ContentLoaded
    -0.57
    Obrázky
    -0.56
    ModelSerializer
    -0.55
    ftagPool
    -0.52
    XmlAccessorType
    -0.51
    AccessorTable
    -0.50
    jectures
    -0.50
    المكان
    -0.49
    cioni
    -0.49
    nologue
    -0.48
    POSITIVE LOGITS
     Italijanski
    0.48
     disponibilités
    0.40
    VS
    0.38
     Between
    0.38
     tartalomajánló
    0.38
     the
    0.36
    Between
    0.36
     mellem
    0.36
    mergeFrom
    0.36
     Италијани
    0.35
    Activations Density 0.515%

    No Known Activations