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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9373
    Prev
    Next
    INDEX
    Explanations

    quantitative assessments of agreement or diagnosis in medical contexts

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

    Numbers followed by "to"

    np_acts-logits-general · gemini-2.0-flash

    moderate to severe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    ]--;
    -0.84
    +#+#
    -0.65
    ChildScrollView
    -0.65
    الإنجليزية
    -0.65
     atra
    -0.64
     مرئيه
    -0.64
    новниш
    -0.62
    ()")
    -0.61
    </tfoot>
    -0.61
    はじめに
    -0.60
    POSITIVE LOGITS
     až
    1.10
     hingga
    1.01
    -£
    1.01
    ~
    0.99
    –
    0.98
     sampai
    0.96
    至
    0.90
     الی
    0.90
    〜
    0.85
     până
    0.84
    Activations Density 1.236%

    No Known Activations