© 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. 10-GEMMASCOPE-RES-16K
    11. 15628
    Prev
    Next
    INDEX
    Explanations

    variations and corrections related to spelling and name variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.58
    aktery
    -0.47
     հղումներ
    -0.46
    RenderAtEndOf
    -0.45
     hırka
    -0.44
    jsonwebtoken
    -0.43
    providedIn
    -0.43
    artamento
    -0.43
    tagHelper
    -0.42
     Italijani
    -0.42
    POSITIVE LOGITS
     spelling
    0.80
     spelled
    0.70
    spelling
    0.70
     missp
    0.69
     misspelled
    0.64
     spell
    0.64
     spelt
    0.61
    spell
    0.59
     pronouncing
    0.59
     Spelling
    0.57
    Activations Density 0.669%

    No Known Activations