© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 849
    Prev
    Next
    INDEX
    Explanations

    phrases indicating multiple elements or components in various contexts

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

    quantity/multiplicity

    np_acts-logits-general · gemini-2.0-flash

    multiple counts

    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
    borderFill
    -0.48
    出版年
    -0.47
     faltan
    -0.44
     wygląda
    -0.44
    reste
    -0.43
     recevrez
    -0.43
     aplican
    -0.43
     gestes
    -0.43
     sequência
    -0.42
    ScopeManager
    -0.42
    POSITIVE LOGITS
     Multiple
    0.60
     multiple
    0.60
     MULTIPLE
    0.58
    Multiple
    0.52
    multiple
    0.52
     simultaneous
    0.45
    MULTIPLE
    0.44
    Tikang
    0.42
     coö
    0.41
    simult
    0.41
    Activations Density 0.640%

    No Known Activations