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. 31-GEMMASCOPE-RES-16K
    6. 16333
    Prev
    Next
    INDEX
    Explanations

    concepts related to rarity and unusual medical conditions

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

    followed by rarity adjectives

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.75
     resourceCulture
    -0.65
    parsedMessage
    -0.61
     مشين
    -0.58
    MigrationBuilder
    -0.57
    醐
    -0.55
    JspWriter
    -0.54
     nonUne
    -0.50
    Hozzáférés
    -0.49
    rrggbb
    -0.49
    POSITIVE LOGITS
     rare
    2.84
    Rare
    2.47
    rare
    2.42
     Rare
    2.28
     rarely
    2.23
     rarity
    2.22
     rares
    2.22
     rarer
    2.22
     RARE
    2.14
     rarest
    2.13
    Activations Density 0.659%

    No Known Activations