© 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. 0-GEMMASCOPE-RES-16K
    11. 2671
    Prev
    Next
    INDEX
    Explanations

    mentions of mountains and related geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dedicated
    -0.52
    <strong>
    -0.48
    <em>
    -0.46
    ten
    -0.46
    <h1>
    -0.45
     benefited
    -0.45
     pronounced
    -0.44
    ありません
    -0.43
    The
    -0.43
    4
    -0.43
    POSITIVE LOGITS
     myſelf
    0.70
    SourceChecksum
    0.67
     stays
    0.65
    verwijspagina
    0.63
     ſta
    0.63
    twimg
    0.63
     ویکی‌پدیا
    0.63
     Савезне
    0.60
     Mountain
    0.59
     Theſe
    0.59
    Activations Density 0.243%

    No Known Activations