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. 15-GEMMASCOPE-RES-16K
    6. 2400
    Prev
    Next
    INDEX
    Explanations

    key phrases related to causation and relationships within complex systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.66
    windowFixed
    -0.65
    MigrationBuilder
    -0.63
    rawDesc
    -0.62
     ſeveral
    -0.58
     myſelf
    -0.58
    __(/*!
    -0.58
    ArrowToggle
    -0.58
     greateſt
    -0.57
     ſche
    -0.55
    POSITIVE LOGITS
    makeText
    0.70
     cause
    0.61
     disambiguazione
    0.58
     kolei
    0.58
     doom
    0.53
     guide
    0.50
    caused
    0.48
    keyed
    0.48
    把
    0.48
     chave
    0.47
    Activations Density 0.460%

    No Known Activations