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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 10225
    Prev
    Next
    INDEX
    Explanations

    instances of the word "beat" in various contexts, often relating it to physical actions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.74
    ‍♀️
    -0.66
    rogels
    -0.66
    unhofer
    -0.64
    NVIDIA
    -0.63
    argb
    -0.62
    Coy
    -0.62
    复制代码
    -0.62
    ObjectID
    -0.61
     TCG
    -0.60
    POSITIVE LOGITS
     beat
    2.77
     BEAT
    2.61
     Beat
    2.53
     beats
    2.49
    beat
    2.39
    Beat
    2.36
     beating
    2.34
    BEAT
    2.23
     Beats
    2.20
     beaten
    2.16
    Activations Density 0.050%

    No Known Activations