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. 12-GEMMASCOPE-RES-16K
    6. 15895
    Prev
    Next
    INDEX
    Explanations

    references to different times of day, specifically afternoons and related descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ########.
    -0.72
     velas
    -0.65
    HasKey
    -0.63
     Wirt
    -0.63
     keras
    -0.62
    keras
    -0.62
     Kyrie
    -0.62
     Blackwell
    -0.62
     ModelExpression
    -0.62
    евский
    -0.61
    POSITIVE LOGITS
     afternoon
    1.34
     Afternoon
    1.33
    Afternoon
    1.26
    noons
    1.24
    NOON
    1.23
    afternoon
    1.11
     afternoons
    1.11
     noon
    1.07
     lunch
    1.05
    noon
    1.03
    Activations Density 0.071%

    No Known Activations