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. 16-GEMMASCOPE-RES-16K
    6. 6588
    Prev
    Next
    INDEX
    Explanations

    elements that indicate comparisons or contrasts in the text

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

    Follows punctuation, conjunctions, or currency symbols

    np_acts-logits-general · gemini-2.0-flash

    proper nouns and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.81
     للاسماء
    -0.72
     الرياضيه
    -0.71
     Pyrene
    -0.71
    extAlignment
    -0.68
    akaian
    -0.64
     itſelf
    -0.64
     Reſ
    -0.62
     raiſ
    -0.61
     IUPAC
    -0.61
    POSITIVE LOGITS
     Har
    0.62
     K
    0.61
     Bal
    0.60
    ględ
    0.59
     Bar
    0.58
     B
    0.57
     Sa
    0.56
    Autres
    0.56
    Outras
    0.56
     O
    0.56
    Activations Density 0.850%

    No Known Activations