© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 12876
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and structures related to matrices and vectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.41
    wapV
    -0.37
    ┻
    -0.36
     Hoo
    -0.35
    <0xD7>
    -0.33
    存于互联网档案馆
    -0.33
    󠁬
    -0.33
    pecto
    -0.32
    Op
    -0.32
    Története
    -0.31
    POSITIVE LOGITS
     ModelExpression
    0.75
    RegressionTest
    0.58
    appartamento
    0.52
     uLocal
    0.50
    PerformLayout
    0.50
    XmlEnum
    0.50
    PostInfinity
    0.49
    #+#
    0.47
    省市镇
    0.47
     GRADUATE
    0.46
    Activations Density 0.522%

    No Known Activations