Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 2866
    Prev
    Next
    INDEX
    Explanations

    patterns related to GitHub URL structures and repository information

    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
     Pfeffer
    -0.54
     يتيمه
    -0.50
    orianCalendar
    -0.49
    Diwedd
    -0.47
     surla
    -0.47
    Tembelea
    -0.46
     voti
    -0.45
    RenderAtEndOf
    -0.44
    DRAG
    -0.43
    ValueStyle
    -0.43
    POSITIVE LOGITS
     split
    1.35
    split
    1.26
    Split
    1.13
     Split
    1.13
     splits
    1.00
     splitting
    0.93
    SPLIT
    0.90
     trim
    0.86
    replace
    0.85
     replace
    0.82
    Activations Density 0.355%

    No Known Activations