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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 15296
    Prev
    Next
    INDEX
    Explanations

    excessive use of the word "too" and general expressions of excessiveness or inconsistency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.46
    imdi
    -0.42
    inguém
    -0.42
    parsedMessage
    -0.41
     Biôgrafia
    -0.40
     مشين
    -0.40
     defaultstate
    -0.39
     intégral
    -0.39
     ninguém
    -0.38
    bunya
    -0.37
    POSITIVE LOGITS
     too
    1.03
     Too
    0.97
    too
    0.93
     слишком
    0.90
    Too
    0.89
     terlalu
    0.88
     insufficient
    0.86
     zbyt
    0.85
     troppo
    0.79
     TOO
    0.79
    Activations Density 0.512%

    No Known Activations