© 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. 10534
    Prev
    Next
    INDEX
    Explanations

    references to a specific subject or theme, particularly focusing on words like "her", "this", "that", and "which"

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

    Preceding words of varied topics and contexts

    np_acts-logits-general · gemini-2.0-flash

    Massive hemorrhage

    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
    -0.97
     للاسماء
    -0.96
    setVerticalGroup
    -0.93
    GEBURTSDATUM
    -0.91
    Hentet
    -0.89
    DockStyle
    -0.87
    HtmlAttribute
    -0.85
    <unused42>
    -0.85
    <unused43>
    -0.85
     мәкал
    -0.85
    POSITIVE LOGITS
    ,
    0.39
     at
    0.34
     for
    0.34
     in
    0.33
    ナル
    0.30
    .
    0.29
     with
    0.29
    1
    0.28
     to
    0.28
     by
    0.27
    Activations Density 0.453%

    No Known Activations