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. 10251
    Prev
    Next
    INDEX
    Explanations

    instances where terms or phrases denote actions, events, or entities occurring in specific contexts

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

    Prepositions followed by possessive pronouns or "San"

    np_acts-logits-general · gemini-2.0-flash

    in, of, for, to, during

    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
    \|_{\
    -0.49
    tagHelper
    -0.47
    ︎
    -0.45
     кӀ
    -0.45
    انگلیسی
    -0.45
     ISSN
    -0.44
    washingtonpost
    -0.44
    gridx
    -0.43
     us
    -0.43
    """.
    -0.42
    POSITIVE LOGITS
     årets
    0.84
     our
    0.71
     veck
    0.71
    Vidite
    0.67
    endphp
    0.66
     their
    0.65
     NUKAT
    0.62
     CreateTagHelper
    0.60
     cowok
    0.60
     Wikimedijinoj
    0.59
    Activations Density 0.478%

    No Known Activations