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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1068
    Prev
    Next
    INDEX
    Explanations

    scientific terms and specific molecular processes related to chemistry and biology

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

    scientific word parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Mir
    -0.43
     coag
    -0.42
    Lähteet
    -0.42
     Poverty
    -0.42
    }-*/;
    -0.42
     Schna
    -0.41
    grafa
    -0.40
    hawks
    -0.40
     maxim
    -0.40
     Portable
    -0.39
    POSITIVE LOGITS
    RenderAtEndOf
    0.80
     EconPapers
    0.79
    LookAnd
    0.59
    SharedDtor
    0.58
     utafitiHapana
    0.57
     betweenstory
    0.57
    Datuak
    0.52
    ChildScrollView
    0.49
     intStringLen
    0.48
     MainAxisSize
    0.48
    Activations Density 0.056%

    No Known Activations