© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 111278
    Prev
    Next
    INDEX
    Explanations

    sections of text that relate to LaTeX formatting and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     يتيمه
    -0.91
    EDEFAULT
    -0.81
     OMITBAD
    -0.81
     Roskov
    -0.79
     ویکی‌پدی
    -0.77
     Meksiku
    -0.73
     ujednoznacz
    -0.71
    IsContent
    -0.69
    цезда
    -0.69
     ***!
    -0.68
    POSITIVE LOGITS
     We
    0.39
     etc
    0.35
     The
    0.34
     Estamos
    0.34
     Just
    0.34
    import
    0.33
     It
    0.33
     Secretaria
    0.33
     halus
    0.33
     and
    0.33
    Activations Density 0.000%

    No Known Activations