Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 9599
    Prev
    Next
    INDEX
    Explanations

    terms related to legal professionals and the concept of manifesting or expressing something formally

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.66
    coroutines
    -0.65
    persky
    -0.62
     lit
    -0.61
     Alen
    -0.60
     Sols
    -0.59
    โซ
    -0.58
    eadas
    -0.57
     sur
    -0.57
    Chore
    -0.56
    POSITIVE LOGITS
    RenderAtEndOf
    0.95
    Rams
    0.95
     Ramsay
    0.89
     itſelf
    0.85
     Rams
    0.82
     Civilization
    0.78
     civilization
    0.77
     Llama
    0.77
     Wakefield
    0.76
     raiſ
    0.75
    Activations Density 0.062%

    No Known Activations