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. 9-GEMMASCOPE-RES-16K
    6. 6879
    Prev
    Next
    INDEX
    Explanations

    terms related to writing, content creation, and graphic design

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

    writing, editing, and publishing

    np_acts-logits-general · gemini-2.0-flash

    writer, copy, and print media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.55
    StructEnd
    -0.45
    écnicas
    -0.39
     ModelRenderer
    -0.39
    oredCriteria
    -0.37
     wezen
    -0.36
    TagMode
    -0.36
     &___
    -0.36
    upiter
    -0.35
    autoIncrement
    -0.34
    POSITIVE LOGITS
     Typography
    0.63
     typography
    0.61
     ModelExpression
    0.59
     Freelance
    0.56
    文案
    0.55
     éditoriale
    0.55
     freelance
    0.52
    typography
    0.52
     freelancers
    0.52
    writers
    0.49
    Activations Density 0.335%

    No Known Activations