© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 1819
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to images and collections found on websites

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

    Followed by "from", "on", or "to"

    np_acts-logits-general · gemini-2.0-flash

    pictures, images, and sales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     run
    -0.36
     —
    -0.35
     own
    -0.35
     push
    -0.35
    —
    -0.34
     next
    -0.34
     and
    -0.34
     then
    -0.33
    enschaften
    -0.33
     as
    -0.32
    POSITIVE LOGITS
    出版年
    0.83
    RectangleBorder
    0.70
    httphttps
    0.68
    GEBURTSDATUM
    0.68
    Obrázky
    0.67
    ValueStyle
    0.66
     HasFactory
    0.66
     nakalista
    0.66
    таратура
    0.65
    
    0.65
    Activations Density 0.351%

    No Known Activations