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. 31-GEMMASCOPE-RES-16K
    6. 15511
    Prev
    Next
    INDEX
    Explanations

    key figures and organizations involved in genomic research

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

    Iceland and Icelandic related words

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.50
    磚
    -0.46
    tagext
    -0.46
     otomatig
    -0.45
    nasium
    -0.44
    exitRule
    -0.43
     Malaya
    -0.42
     Serikat
    -0.41
     Italijanski
    -0.40
     canst
    -0.40
    POSITIVE LOGITS
     Iceland
    1.16
     Icelandic
    1.13
    Iceland
    1.08
     Reykjavik
    0.90
     Reykjav
    0.81
    ykjav
    0.76
    celand
    0.53
    ð
    0.52
     Þ
    0.52
     Thors
    0.51
    Activations Density 0.064%

    No Known Activations