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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1095
    Prev
    Next
    INDEX
    Explanations

    references to fashionable or trendy individuals and lifestyle elements

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

    Follows prepositions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    patients, players, then names, purchasing, or roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ar
    -0.30
     Ar
    -0.29
    soort
    -0.29
    か月
    -0.26
     Taken
    -0.25
     taken
    -0.25
     shell
    -0.25
     Ahnung
    -0.25
     Gutes
    -0.25
    Ar
    -0.24
    POSITIVE LOGITS
    expandindo
    0.85
     للمعارف
    0.77
    webElementXpaths
    0.77
     vegetarians
    0.74
    readers
    0.73
    DIPSETTING
    0.73
     readers
    0.72
     gardeners
    0.71
     propOrder
    0.71
    XmlAccessType
    0.70
    Activations Density 0.183%

    No Known Activations