© 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. 30-GEMMASCOPE-RES-16K
    11. 12523
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to inquiries or requesting information

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

    French language

    np_acts-logits-general · gemini-2.0-flash

    French phrases or medical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pouvoit
    -0.52
     aikaa
    -0.48
     actuels
    -0.48
    HtmlAttribute
    -0.46
    DockStyle
    -0.46
     TAMBÉM
    -0.46
     dezelve
    -0.46
     âmes
    -0.46
     actualidad
    -0.46
    aronder
    -0.46
    POSITIVE LOGITS
    writeFieldEnd
    0.42
     surla
    0.40
     thing
    0.39
    tiness
    0.39
    ๆ
    0.36
    getChildAt
    0.36
     debu
    0.35
    Ther
    0.35
     vý
    0.35
     das
    0.34
    Activations Density 0.029%

    No Known Activations