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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1897
    Prev
    Next
    INDEX
    Explanations

    instances of the word "clock" and related terminology associated with timing and oscillation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kveld
    -0.84
     vettoriale
    -0.83
    NegativeButton
    -0.83
    <?=
    -0.82
    Capítulo
    -0.82
    anskje
    -0.81
     volgt
    -0.81
    Portale
    -0.80
     Bevan
    -0.79
    HttpEntity
    -0.78
    POSITIVE LOGITS
     CLOCK
    1.82
     clock
    1.70
     Clock
    1.65
     clocks
    1.63
     Clocks
    1.57
    clock
    1.53
    Clock
    1.50
    CLOCK
    1.38
     clocked
    1.16
     klo
    0.88
    Activations Density 0.037%

    No Known Activations