© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11972
    Prev
    Next
    INDEX
    Explanations

    references to ongoing challenges and struggles experienced by characters or individuals

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

    duration or time passed

    np_acts-logits-general · gemini-2.0-flash

    always been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     Verhältnisse
    -0.61
    )++;
    -0.54
     nanti
    -0.50
    ksikon
    -0.50
    BagConstraints
    -0.50
    ugc
    -0.49
    ﾟ)
    -0.49
     uusi
    -0.47
    aliana
    -0.47
     nächste
    -0.46
    POSITIVE LOGITS
     since
    0.82
     depuis
    0.70
     seit
    0.69
    depuis
    0.68
    since
    0.67
    一直
    0.66
     been
    0.65
     lately
    0.63
     Desde
    0.63
    以来
    0.62
    Activations Density 0.337%

    No Known Activations