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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10087
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "moment" and its variations

    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
     paroisse
    -0.72
     HttpNotFound
    -0.67
    jillo
    -0.67
    jaciół
    -0.66
     contratto
    -0.65
     charité
    -0.60
     noastre
    -0.60
     grátis
    -0.59
     jullie
    -0.59
    zieży
    -0.58
    POSITIVE LOGITS
     moment
    3.43
    moment
    3.19
    Moment
    3.10
     Moment
    3.09
     moments
    3.05
     MOMENT
    2.79
     Moments
    2.78
    moments
    2.75
    Moments
    2.68
     momento
    2.19
    Activations Density 0.051%

    No Known Activations