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. 21-GEMMASCOPE-RES-16K
    6. 12417
    Prev
    Next
    INDEX
    Explanations

    references to weekends and Sunday activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.59
     Thursdays
    -0.58
    Thursday
    -0.54
     Donnerstag
    -0.54
     Thursday
    -0.53
    mac
    -0.50
    THURSDAY
    -0.50
    gawai
    -0.49
     jeudi
    -0.49
    staun
    -0.49
    POSITIVE LOGITS
     Sunday
    1.73
    Sunday
    1.64
    sunday
    1.47
     SUNDAY
    1.47
     sunday
    1.44
     Sundays
    1.42
    SUNDAY
    1.40
     domingo
    1.30
     dimanche
    1.26
     domenica
    1.20
    Activations Density 0.097%

    No Known Activations