© 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. 20-GEMMASCOPE-RES-16K
    11. 6637
    Prev
    Next
    INDEX
    Explanations

    occurrences of web domains or URLs

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

    domain names or website URLs.

    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
     ModelExpression
    -0.71
     ſind
    -0.66
    iſten
    -0.65
     MainAxisSize
    -0.63
    iſen
    -0.61
    WriteTagHelper
    -0.61
    '},
    -0.60
    "],
    -0.60
    \{\\
    -0.60
     CreateTagHelper
    -0.60
    POSITIVE LOGITS
    com
    0.82
    org
    0.56
    http
    0.46
    URLException
    0.45
    COM
    0.45
     www
    0.43
    www
    0.43
    Com
    0.42
     http
    0.42
     com
    0.41
    Activations Density 0.065%

    No Known Activations