Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10359
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to figures or images within a scientific context

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

    Followed by specific letters

    np_acts-logits-general · gemini-2.0-flash

    letters within parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    intios
    -0.52
    anema
    -0.48
    тона
    -0.45
    +:+
    -0.44
    нос
    -0.44
    4
    -0.44
    Cause
    -0.44
     splits
    -0.43
    5
    -0.42
    cob
    -0.42
    POSITIVE LOGITS
     ویکی‌پدیای
    0.69
    uxxxx
    0.68
    ⓧ
    0.59
    extAlignment
    0.58
     useRouter
    0.58
    Литература
    0.57
    orteur
    0.57
     ThemeData
    0.57
     مرئيه
    0.55
     Redacción
    0.55
    Activations Density 0.411%

    No Known Activations