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. 3393
    Prev
    Next
    INDEX
    Explanations

    references to models and frameworks related to programming or software development

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

    Code, paths, or file names

    np_acts-logits-general · gemini-2.0-flash

    model lease properties

    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
     فريبيس
    -0.80
    DockStyle
    -0.76
     يتيمه
    -0.75
     arşivlendi
    -0.74
    CppMethod
    -0.74
    المناصب
    -0.73
     ModelExpression
    -0.73
     ProtoMessage
    -0.70
    awtextra
    -0.68
     NSCoder
    -0.68
    POSITIVE LOGITS
     pec
    0.35
    model
    0.35
     Google
    0.33
     Earth
    0.31
    swift
    0.30
    Google
    0.30
    Earth
    0.29
    Swift
    0.29
     google
    0.29
     EARTH
    0.29
    Activations Density 0.006%

    No Known Activations