© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8182
    Prev
    Next
    INDEX
    Explanations

    mentions of tech companies and electronic products

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

    followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    negative or ending states

    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
    aarrggbb
    -0.70
     متعلقه
    -0.68
    ftagPool
    -0.68
    الإنجليزية
    -0.64
    parsedMessage
    -0.63
    ########.
    -0.63
    MessageTagHelper
    -0.60
    makeText
    -0.56
    *{\
    -0.55
    المناصب
    -0.55
    POSITIVE LOGITS
     anymore
    1.18
     unless
    1.08
     nor
    1.07
    unless
    0.94
     any
    0.90
    akaan
    0.88
     tampoco
    0.83
     nici
    0.81
     enää
    0.79
     apapun
    0.78
    Activations Density 0.688%

    No Known Activations