© 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. 28-GEMMASCOPE-RES-16K
    11. 7644
    Prev
    Next
    INDEX
    Explanations

    technical terminologies related to scientific processes and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Light, beams, and particle interaction

    np_acts-logits-general · gemini-2.0-flash

    passing or interacting light/particles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ainfi
    -0.55
    expandindo
    -0.55
    RenderAtEndOf
    -0.48
     reopened
    -0.46
    تقاوى
    -0.44
     ſtand
    -0.43
    ChildScrollView
    -0.42
     oreilles
    -0.42
     debout
    -0.41
    IsOpen
    -0.40
    POSITIVE LOGITS
     penetrate
    0.73
     penetrating
    0.71
     penetrates
    0.69
     passing
    0.66
     entering
    0.65
     traversing
    0.63
     landing
    0.62
     hitting
    0.59
     passes
    0.58
     enters
    0.57
    Activations Density 0.867%

    No Known Activations