© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 11149
    Prev
    Next
    INDEX
    Explanations

    references to education and professional development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Quote introductions to speech

    np_acts-logits-general · gemini-2.0-flash

    spoken attribution after dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.43
     utterly
    -0.38
     FUCKING
    -0.37
     fucking
    -0.37
     hugely
    -0.36
     Soho
    -0.33
     sophisticated
    -0.33
     sobretudo
    -0.32
     precisely
    -0.32
    是我们
    -0.32
    POSITIVE LOGITS
     
    0.65
    PyExc
    0.64
    parsedMessage
    0.64
    MigrationBuilder
    0.63
     employes
    0.63
     препратки
    0.59
    IntoConstraints
    0.59
    IContainer
    0.58
    domada
    0.57
     كومونز
    0.57
    Activations Density 0.272%

    No Known Activations