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. 16-GEMMASCOPE-RES-16K
    6. 8945
    Prev
    Next
    INDEX
    Explanations

    terms related to regeneration in biological contexts

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

    "regener" or nitrogen-related tokens

    np_acts-logits-general · gemini-2.0-flash

    regener, NH names, pistol, fellow

    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
     useContext
    -0.73
    enzie
    -0.66
    emf
    -0.66
    ان
    -0.65
    ทธิ
    -0.65
    age
    -0.63
     Buon
    -0.60
    icht
    -0.60
     Jas
    -0.59
    rictive
    -0.59
    POSITIVE LOGITS
    adaptiveStyles
    0.91
    RenderAtEndOf
    0.85
     Yunus
    0.85
     ➢
    0.84
     varandra
    0.80
    enedor
    0.80
     Varela
    0.79
     Brunner
    0.78
     Searle
    0.78
     poffe
    0.75
    Activations Density 0.874%

    No Known Activations