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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 15001
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fall" and its variations, indicating themes related to emotional or physical descent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RadioGroup
    -0.76
     دیکھیے
    -0.72
    ürger
    -0.63
     Robson
    -0.62
    rettet
    -0.61
     gani
    -0.59
    geschlossen
    -0.59
    aufnahme
    -0.58
    gräns
    -0.58
    ηγ
    -0.58
    POSITIVE LOGITS
    FALL
    1.79
    fall
    1.72
     FALL
    1.71
     fall
    1.68
     Fall
    1.60
    Fall
    1.59
    Falls
    1.58
     falls
    1.57
    falling
    1.57
    falls
    1.55
    Activations Density 0.056%

    No Known Activations