© 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. 5478
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols in the text

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

    scientific or technical terminology and statistical notation.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
    protoimpl
    -0.56
     мәкал
    -0.54
    listdir
    -0.54
    __*/
    -0.53
    SequentialGroup
    -0.53
     الحره
    -0.52
     textStatus
    -0.50
     embarazadas
    -0.50
    ksesta
    -0.49
    Билгалдахарш
    -0.48
    POSITIVE LOGITS
    subsection
    0.93
    subsubsection
    0.92
    ReusableCell
    0.44
    }{*}{}
    0.39
    HomeAsUpEnabled
    0.36
    richTextPanel
    0.36
    bibitem
    0.35
    __":
    0.35
    employeeId
    0.35
    IntoConstraints
    0.34
    Activations Density 0.052%

    No Known Activations