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. 15-GEMMASCOPE-RES-16K
    6. 1713
    Prev
    Next
    INDEX
    Explanations

    references to timing and frequency of events

    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
    MemoryWarning
    -0.49
    CHOICES
    -0.47
    HttpHeaders
    -0.47
    hyrchwyd
    -0.45
    initializeApp
    -0.45
    IVEREF
    -0.44
    FormState
    -0.43
    ьере
    -0.41
    posedge
    -0.41
    centralwidget
    -0.40
    POSITIVE LOGITS
     unusually
    1.25
    Unusual
    1.18
     unexpectedly
    1.12
     unusual
    1.11
     inusual
    1.09
     Unusual
    1.09
     instead
    1.07
     abnormally
    1.06
     atypical
    1.05
     unexpected
    1.05
    Activations Density 0.434%

    No Known Activations