© 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. 24-GEMMASCOPE-RES-16K
    11. 5814
    Prev
    Next
    INDEX
    Explanations

    concepts related to critique of economic theories and their relevance

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

    Academic or scientific study

    np_acts-logits-general · gemini-2.0-flash

    scientific research and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.63
    tagext
    -0.55
    +#+
    -0.52
    RenderAtEndOf
    -0.50
    copg
    -0.49
    VersionUID
    -0.48
     otomatig
    -0.47
    ₡
    -0.47
    ConstraintMaker
    -0.45
     coö
    -0.43
    POSITIVE LOGITS
     research
    0.56
     methodological
    0.54
     historical
    0.52
     bilim
    0.52
     studies
    0.50
     scientific
    0.49
     methodologies
    0.49
     języka
    0.49
     paradigms
    0.49
     readers
    0.48
    Activations Density 0.669%

    No Known Activations