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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 111544
    Prev
    Next
    INDEX
    Explanations

    elements related to optical density and assay measurement processes

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

    intensity, optical density, absorbance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.59
    reathe
    -0.49
     Hero
    -0.48
    enumii
    -0.47
    StructEnd
    -0.47
     MediatR
    -0.46
     QM
    -0.45
     MCM
    -0.45
    localctx
    -0.45
    ValueStyle
    -0.43
    POSITIVE LOGITS
     Pakai
    0.47
     miniaturka
    0.47
     förr
    0.47
     Flasche
    0.47
    řevě
    0.46
     jelas
    0.46
     vergüenza
    0.45
     Verhält
    0.45
     Verhältnisse
    0.45
     Auft
    0.44
    Activations Density 0.253%

    No Known Activations