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. 61666
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and lineage

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

    family members and names

    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
    GEBURTSDATUM
    -0.39
    Carriera
    -0.34
    rosi
    -0.33
    iestety
    -0.33
    ppuden
    -0.33
     счита
    -0.33
    elerik
    -0.33
    DMETHOD
    -0.32
     Dobson
    -0.32
    SharedDtor
    -0.32
    POSITIVE LOGITS
    AndEndTag
    0.59
     Ahnung
    0.51
    transQ
    0.48
    ReusableCell
    0.46
     pince
    0.45
    MLLoader
    0.44
    VersionUID
    0.44
    Portály
    0.43
    __*/
    0.43
     informée
    0.42
    Activations Density 0.009%

    No Known Activations