© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15677
    Prev
    Next
    INDEX
    Explanations

    references to specific days and their significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the phrase "day-to-day" or "day" used as a temporal descriptor in compound expressions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.58
    :✨
    -0.41
     تضيفلها
    -0.40
    politico
    -0.37
     ממ
    -0.37
     femininas
    -0.37
    ModelAttribute
    -0.37
    -------
    -0.36
     vidare
    -0.35
     mobilya
    -0.35
    POSITIVE LOGITS
    dream
    0.66
    dreaming
    0.64
    tagext
    0.60
    AnchorStyles
    0.56
    OfWeek
    0.54
    OfMonth
    0.54
     layui
    0.54
    dreams
    0.53
    DAY
    0.52
    semana
    0.51
    Activations Density 0.142%

    No Known Activations