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. 3-GEMMASCOPE-RES-16K
    6. 11096
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "tap" and its variations, indicating discussions around tapping or interaction in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rimidine
    -0.62
     umat
    -0.60
    classNames
    -0.60
    coy
    -0.59
    naco
    -0.58
    traje
    -0.57
    GenerationType
    -0.56
     bezeichneter
    -0.55
    wikimedia
    -0.53
    hicles
    -0.53
    POSITIVE LOGITS
     tap
    3.50
     Tap
    3.27
    Tap
    3.17
     taps
    3.11
    tap
    2.90
     tapping
    2.69
     TAP
    2.67
     tapped
    2.67
    taps
    2.56
    TAP
    2.31
    Activations Density 0.058%

    No Known Activations