© 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. 3-GEMMASCOPE-RES-16K
    11. 8592
    Prev
    Next
    INDEX
    Explanations

    actions and processes related to functions or roles within systems

    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
     ivelany
    -0.68
     iconLine
    -0.60
    httphttps
    -0.59
     wasn
    -0.57
    ConstraintMaker
    -0.56
     CanadaChoose
    -0.53
     Wasn
    -0.52
    endphp
    -0.52
    ContentAsync
    -0.52
    RenderAtEndOf
    -0.51
    POSITIVE LOGITS
     are
    0.60
     prowadzi
    0.56
     takes
    0.53
     vannak
    0.52
    raszamy
    0.52
     gives
    0.52
     znajdują
    0.51
     spelar
    0.50
     argint
    0.50
     enters
    0.50
    Activations Density 1.273%

    No Known Activations