© 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. 3-GEMMASCOPE-RES-16K
    11. 3116
    Prev
    Next
    INDEX
    Explanations

    repeated sequences of characters or patterns within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Comprometido
    -0.49
    QMetaType
    -0.48
     sumpay
    -0.47
     مرئيه
    -0.46
    нгред
    -0.45
    }-*/;
    -0.44
     pérd
    -0.44
    webElementGuid
    -0.44
     Infór
    -0.43
     continuidad
    -0.42
    POSITIVE LOGITS
    x
    0.75
     x
    0.56
     Audiodateien
    0.55
     ujednoznacz
    0.54
    X
    0.45
     Thought
    0.43
     Thoughts
    0.42
    enumi
    0.40
    thing
    0.39
     thought
    0.39
    Activations Density 0.239%

    No Known Activations