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. 2802
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and actions related to decision-making or significant 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
    nitř
    -0.47
     forti
    -0.46
     height
    -0.43
    ấy
    -0.41
     mutual
    -0.40
    OTROS
    -0.39
    ibig
    -0.39
     equivale
    -0.39
    étaire
    -0.38
     refleja
    -0.38
    POSITIVE LOGITS
     himself
    1.31
    WithIOException
    1.03
    himself
    1.02
    httphttps
    0.98
    تقاوى
    0.97
     his
    0.95
    verwijspagina
    0.95
     defaultstate
    0.93
    RenderAtEndOf
    0.90
    SharedDtor
    0.85
    Activations Density 0.907%

    No Known Activations