© 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. 5587
    Prev
    Next
    INDEX
    Explanations

    references to varying quantities or conditions pertaining to groups or categories

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

    Followed by adjectives or regions

    np_acts-logits-general · gemini-2.0-flash

    introducing examples or specific cases

    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
     EconPapers
    -0.61
    kmale
    -0.55
    Попис
    -0.48
    醐
    -0.48
     surla
    -0.45
    balleur
    -0.44
    ValueStyle
    -0.43
    Халык
    -0.41
     anch
    -0.40
    Климаты
    -0.38
    POSITIVE LOGITS
     certaines
    0.64
     egyes
    0.61
     certain
    0.60
     Certain
    0.59
     sommige
    0.59
    Certain
    0.59
     sometimes
    0.57
    บาง
    0.56
    によっては
    0.56
     vissa
    0.56
    Activations Density 0.332%

    No Known Activations