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. 25-GEMMASCOPE-RES-16K
    6. 4342
    Prev
    Next
    INDEX
    Explanations

    references to dance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 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
     dance
    -1.21
     Dance
    -1.15
    dance
    -1.12
     DANCE
    -1.10
    Dance
    -1.07
     danced
    -1.00
     dancer
    -0.99
     dancing
    -0.98
     dancers
    -0.98
    DANCE
    -0.97
    POSITIVE LOGITS
    StoreMessageInfo
    0.75
    hall
    0.69
    floor
    0.66
    ftagPool
    0.65
    floors
    0.60
    featureID
    0.60
    __*/
    0.58
    !*\
    0.57
    postmedia
    0.55
     floor
    0.54
    Activations Density 0.335%

    No Known Activations