Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8640
    Prev
    Next
    INDEX
    Explanations

    instances of the word "too."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.60
     Infór
    -0.54
     externi
    -0.51
     sufrimiento
    -0.48
    makeText
    -0.47
    UrlResolution
    -0.47
    parsedMessage
    -0.47
    LookAnd
    -0.47
     Biôgrafia
    -0.45
    writeFieldEnd
    -0.45
    POSITIVE LOGITS
     too
    1.45
    too
    1.25
     Too
    1.06
    Too
    0.96
     TOO
    0.93
    TOO
    0.77
     слишком
    0.72
    太
    0.68
     zbyt
    0.67
     troppo
    0.64
    Activations Density 0.348%

    No Known Activations