© 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. 39-GEMMASCOPE-RES-16K
    11. 3303
    Prev
    Next
    INDEX
    Explanations

    references to prominent individuals and their roles in events or organizations

    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
    RenderAtEndOf
    -0.57
    EndContext
    -0.52
    Diweddarwch
    -0.52
     Vikipedi
    -0.49
    !*\
    -0.46
    :✨
    -0.44
    ConstraintMaker
    -0.43
    uxxxx
    -0.42
     surla
    -0.42
    Portály
    -0.41
    POSITIVE LOGITS
     speech
    2.02
     speaker
    1.92
     speeches
    1.91
     speaking
    1.85
     speakers
    1.84
     lecture
    1.70
     Speech
    1.62
     Speakers
    1.60
     speak
    1.60
    speaker
    1.56
    Activations Density 0.588%

    No Known Activations