© 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. 24-GEMMASCOPE-RES-16K
    6. 1640
    Prev
    Next
    INDEX
    Explanations

    references to placing or positioning items or concepts

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

    "Place", "complaint", or "error"

    np_acts-logits-general · gemini-2.0-flash

    place, places, placing, placed

    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
    RectangleBorder
    -0.62
     Guten
    -0.57
     borboleta
    -0.49
    retudo
    -0.49
     Bono
    -0.48
    bosity
    -0.48
    Werdegang
    -0.48
     Sew
    -0.47
    Související
    -0.47
     queryParams
    -0.47
    POSITIVE LOGITS
    place
    0.92
    PLACE
    0.82
     PLACE
    0.78
    Place
    0.77
     Place
    0.74
     place
    0.66
    Pla
    0.65
     PLAC
    0.65
     Placing
    0.63
    Placed
    0.62
    Activations Density 0.111%

    No Known Activations