© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7384
    Prev
    Next
    INDEX
    Explanations

    specific scientific and technical terms related to materials and processes

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

    fabric and material terms used in cloth diapering and scientific procedures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.49
    onOptions
    -0.43
    getColumnIndex
    -0.42
     OnTriggerEnter
    -0.37
    AppMethodBeat
    -0.37
    autoreleasepool
    -0.36
    PreExecute
    -0.36
    CppMethod
    -0.36
    writerow
    -0.35
    basicConfig
    -0.35
    POSITIVE LOGITS
     AssemblyVersion
    0.67
    yyj
    0.53
     nahilalakip
    0.52
    Билгалдахарш
    0.49
    twimg
    0.49
     AttributeSet
    0.48
     enfans
    0.48
     jsPsych
    0.47
    bibfield
    0.47
    bootstrapcdn
    0.47
    Activations Density 0.797%

    No Known Activations