© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 12803
    Prev
    Next
    INDEX
    Explanations

    common phrases or expressions indicating conclusion or summarization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.59
    MessageOf
    -0.56
    IntoConstraints
    -0.56
     ujednoznacz
    -0.55
    webElementXpaths
    -0.54
    msgTypes
    -0.52
    SequentialGroup
    -0.51
    yntaxException
    -0.50
     ModelExpression
    -0.50
     resourceCulture
    -0.50
    POSITIVE LOGITS
     finito
    0.51
     thôi
    0.49
     suffice
    0.48
     suffic
    0.47
     FIN
    0.46
     Fin
    0.44
     sufficient
    0.42
    完
    0.41
     Basta
    0.41
     suffices
    0.41
    Activations Density 0.262%

    No Known Activations