Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11493
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to directed graphs and mathematical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Демографія
    -0.55
    SerializedSize
    -0.41
     MainAxisSize
    -0.41
    XmlAccessorType
    -0.40
    lapsingToolbar
    -0.35
    Super
    -0.34
    )_/¯
    -0.34
    perator
    -0.33
     gynnwys
    -0.33
    Jour
    -0.32
    POSITIVE LOGITS
     informée
    0.49
    awtextra
    0.47
    ConstraintMaker
    0.47
    arangay
    0.43
     esternos
    0.43
     للاسماء
    0.43
    IContainer
    0.42
     autorytatywna
    0.42
    disposing
    0.40
    ptonshire
    0.40
    Activations Density 1.605%

    No Known Activations