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. 1068
    Prev
    Next
    INDEX
    Explanations

    the presence of determiners and/or articles in the text

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

    following "the" or "a"

    np_acts-logits-general · gemini-2.0-flash

    German technical terms

    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
     nôtre
    -0.30
     Kebijakan
    -0.29
     Komunikasi
    -0.27
     and
    -0.24
     Fondation
    -0.24
     Serikat
    -0.23
    ành
    -0.23
    creator
    -0.22
     základní
    -0.22
    guruan
    -0.22
    POSITIVE LOGITS
     '\\;'
    0.79
     témoig
    0.78
    iſen
    0.77
     Geiſt
    0.77
    majánló
    0.74
     ſeiner
    0.74
     ſelbſt
    0.73
     ſeines
    0.73
    󠁿
    0.73
     erſten
    0.72
    Activations Density 0.571%

    No Known Activations