© 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-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 2404
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to naming and categorization within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.51
    itinéraire
    -0.43
    Становништво
    -0.42
    SequentialGroup
    -0.42
    تفصیلات
    -0.42
    ClientSize
    -0.41
    setVerticalGroup
    -0.41
    AndroidJUnit
    -0.41
     numberOfRows
    -0.40
    localctx
    -0.39
    POSITIVE LOGITS
     term
    0.77
     terminology
    0.75
     phrase
    0.71
     word
    0.71
     phrases
    0.70
     terms
    0.67
     Phrase
    0.66
     Begriff
    0.65
     palabra
    0.64
     Begriffe
    0.63
    Activations Density 0.693%

    No Known Activations