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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1203
    Prev
    Next
    INDEX
    Explanations

    specific biographical details about individuals

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

    Appearing after punctuation/conjunctions

    np_acts-logits-general · gemini-2.0-flash

    initially began studies

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     שוליים
    -0.80
     ujednoznacz
    -0.58
     հղումներ
    -0.57
    Chham
    -0.56
     Reisedaten
    -0.53
    rrggbb
    -0.51
    oa̍t
    -0.51
     wikipagina
    -0.50
    Datuak
    -0.50
    Derp
    -0.49
    POSITIVE LOGITS
    ide
    0.40
    kształ
    0.34
    Initially
    0.33
    SharedCtor
    0.33
     initial
    0.33
     Initially
    0.31
    Hintergrund
    0.31
     initially
    0.31
    idyl
    0.31
     upbringing
    0.31
    Activations Density 0.200%

    No Known Activations