© 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. 39-GEMMASCOPE-RES-16K
    6. 599
    Prev
    Next
    INDEX
    Explanations

    references to documents, figures, and citations within academic or formal texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enst
    -0.47
    endphp
    -0.46
    ISOL
    -0.42
     Hik
    -0.41
     grass
    -0.41
     Fak
    -0.40
    ){\
    -0.40
    Nel
    -0.39
    ftn
    -0.39
     Ups
    -0.38
    POSITIVE LOGITS
    oneofs
    0.53
    ToBounds
    0.52
     varandra
    0.49
     Walkover
    0.47
     Escolar
    0.47
    afficheront
    0.46
     keş
    0.46
     mourut
    0.44
    帖最后由
    0.43
    apprendre
    0.42
    Activations Density 0.271%

    No Known Activations