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. 12507
    Prev
    Next
    INDEX
    Explanations

    names of educational institutions and professional titles related to education and health services

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

    followed by prepositions/conjunctions

    np_acts-logits-general · gemini-2.0-flash

    administration, hospital, technologies, theatre, montreal, london, association, knights, orchestra

    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
     yourselves
    -0.69
    HttpFoundation
    -0.65
    autoconfigure
    -0.61
    ufact
    -0.59
     ſich
    -0.58
    ्वी
    -0.57
    hdashline
    -0.57
     usu
    -0.57
    iosync
    -0.57
    ecture
    -0.57
    POSITIVE LOGITS
     until
    0.80
    until
    0.65
    tvguidetime
    0.61
     till
    0.58
     UNTIL
    0.57
     untill
    0.55
     during
    0.55
    直到
    0.55
     μέχρι
    0.54
     tätig
    0.53
    Activations Density 0.297%

    No Known Activations