© 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. 12446
    Prev
    Next
    INDEX
    Explanations

    technical and numerical terms related to physical parameters in experiments

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

    quantity or statistics

    np_acts-logits-general · gemini-2.0-flash

    quantifiable measures

    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
    oa̍t
    -0.40
     szerint
    -0.36
    nice
    -0.36
     şekilde
    -0.34
    Nice
    -0.32
    LocationManager
    -0.32
     kerül
    -0.32
     Din
    -0.32
    énario
    -0.31
    Numerology
    -0.30
    POSITIVE LOGITS
     total
    0.91
     estimated
    0.81
     average
    0.80
     overall
    0.79
     maximum
    0.76
     effective
    0.74
     expected
    0.72
     totale
    0.69
     mean
    0.69
     actual
    0.68
    Activations Density 2.091%

    No Known Activations