© 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. 2-GEMMASCOPE-RES-16K
    11. 4232
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the word "fine"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     casquette
    -0.48
    沓
    -0.46
     disambiguazione
    -0.44
     boisson
    -0.43
     wsp
    -0.43
    versary
    -0.42
    🔁
    -0.42
    ViewImports
    -0.42
    ésult
    -0.42
     speranza
    -0.41
    POSITIVE LOGITS
     fine
    4.78
    Fine
    4.31
    fine
    4.25
     Fine
    4.19
     FINE
    3.88
    FINE
    3.53
     finer
    2.63
     fines
    2.42
     finely
    2.25
     finos
    2.09
    Activations Density 0.163%

    No Known Activations