© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10754
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and related terminologies

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

    mathematical equations and formulas, particularly focusing on algebraic expressions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TableBody
    -0.43
    interopRequire
    -0.43
    ंदीखरीदारी
    -0.40
    JsonKey
    -0.39
     autorytatywna
    -0.39
    fjspx
    -0.38
    ppuden
    -0.37
    Viited
    -0.37
    <tfoot>
    -0.37
     Accurate
    -0.37
    POSITIVE LOGITS
    aarrggbb
    0.56
     avoient
    0.52
    URLException
    0.49
    ckså
    0.45
     surla
    0.45
     trouvez
    0.44
    UrlResolution
    0.44
    AndEndTag
    0.44
     fourrure
    0.42
    farol
    0.40
    Activations Density 0.630%

    No Known Activations