© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4067
    Prev
    Next
    INDEX
    Explanations

    specific measurements and concentrations, particularly related to substances in scientific contexts

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

    Units of measurement (mg, g, mmol)

    np_acts-logits-general · gemini-2.0-flash

    numbers and units

    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
     мост
    -0.39
     solas
    -0.36
    Post
    -0.36
    せ
    -0.35
     rounds
    -0.35
     پست
    -0.35
    oltà
    -0.35
    theme
    -0.35
     rosse
    -0.35
    Lines
    -0.35
    POSITIVE LOGITS
     вікісторінку
    0.51
    日閲覧
    0.49
    Werdegang
    0.49
    //};
    0.46
    inelli
    0.46
    >{@
    0.45
    awaiter
    0.45
    pushFollow
    0.44
    ViewInit
    0.44
     onBind
    0.43
    Activations Density 0.770%

    No Known Activations