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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9321
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "fly" and its variants in various contexts related to aviation or celestial themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kháu
    -0.48
     OnInit
    -0.48
     gruesa
    -0.45
     voedsel
    -0.45
     voorbere
    -0.44
    powiedz
    -0.44
     moeite
    -0.43
    /****
    -0.43
     sério
    -0.43
    หนัก
    -0.42
    POSITIVE LOGITS
    Sky
    0.81
     Sky
    0.77
    Cloud
    0.73
     SKY
    0.71
    Fly
    0.70
     flown
    0.68
     cloud
    0.68
     astron
    0.66
    cloud
    0.66
     sky
    0.65
    Activations Density 0.393%

    No Known Activations