© 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. 5638
    Prev
    Next
    INDEX
    Explanations

    words indicating frequency or commonality in various contexts

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

    about commonness or frequency

    np_acts-logits-general · gemini-2.0-flash

    frequency and commonality

    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
    StoryboardSegue
    -0.79
     GenerationType
    -0.71
     مرئيه
    -0.67
     '\\;'
    -0.62
    ViewFeatures
    -0.59
     ModelExpression
    -0.58
    󠁣
    -0.57
    IntoConstraints
    -0.56
     виправивши
    -0.56
     MenuView
    -0.54
    POSITIVE LOGITS
     occurrence
    0.75
     frequent
    0.68
     occurrences
    0.68
     frequency
    0.61
     fréquence
    0.60
     frequently
    0.59
     frecu
    0.56
     frequência
    0.56
     Occurrence
    0.55
     frecuentes
    0.54
    Activations Density 0.523%

    No Known Activations