© 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. 30-GEMMASCOPE-RES-16K
    11. 15180
    Prev
    Next
    INDEX
    Explanations

    historical names and dates

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

    origins or early instances

    np_acts-logits-general · gemini-2.0-flash

    earliest documented origins

    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
    expandindo
    -0.73
     Савезне
    -0.68
     AssemblyCulture
    -0.67
     nahilalakip
    -0.66
     ब्रेकडाउन
    -0.66
     pinulongan
    -0.62
     ProtoMessage
    -0.61
    
    -0.59
     незавершена
    -0.59
    JspWriter
    -0.58
    POSITIVE LOGITS
     records
    1.00
     documented
    0.96
     recorded
    0.88
     historians
    0.86
    documented
    0.77
     documents
    0.77
     evidence
    0.77
     undated
    0.76
     extant
    0.75
    records
    0.75
    Activations Density 0.982%

    No Known Activations