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. 16-GEMMASCOPE-RES-16K
    6. 3052
    Prev
    Next
    INDEX
    Explanations

    the beginning of document segments related to significant concepts or relationships

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

    Text followed by "Q:" or special characters

    np_acts-logits-general · gemini-2.0-flash

    mathematical and programmatic structures

    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
    holdet
    -0.62
     mauvaises
    -0.58
    nestjs
    -0.57
     socialista
    -0.57
     réglable
    -0.55
     econômica
    -0.54
     stedet
    -0.54
     pauvres
    -0.53
     malheureux
    -0.53
     étr
    -0.53
    POSITIVE LOGITS
    MigrationBuilder
    0.64
     kaarangay
    0.60
     BoxFit
    0.56
    tilhe
    0.55
    ablen
    0.54
    EndGlobalSection
    0.53
    脚注の使い方
    0.52
    closes
    0.52
    بوابة
    0.52
    ercizio
    0.51
    Activations Density 0.123%

    No Known Activations