© 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. 2413
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or contexts within a text

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

    the word "in"

    np_acts-logits-general · gemini-2.0-flash

    in the other

    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
    AnchorStyles
    -0.44
     Wikiseite
    -0.33
     dzięki
    -0.32
    inhua
    -0.30
     kõik
    -0.30
     sebagai
    -0.30
    MfG
    -0.30
     насељу
    -0.30
     concluyó
    -0.30
    prnewswire
    -0.29
    POSITIVE LOGITS
     which
    0.69
     '\\;'
    0.68
    contentLoaded
    0.60
     ostavi
    0.60
     تانيه
    0.56
    出版年
    0.54
     defaultstate
    0.54
     Normdatei
    0.54
     које
    0.53
     ويكيميديا
    0.52
    Activations Density 0.669%

    No Known Activations