© 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. 13-GEMMASCOPE-RES-16K
    11. 8468
    Prev
    Next
    INDEX
    Explanations

    patterns of numeric and alphanumeric sequences, likely in a technical or data-related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.72
    الدراسه
    -0.72
     Walkover
    -0.71
    ագրություններ
    -0.69
     Italijanski
    -0.69
    aarrggbb
    -0.69
     صوتيه
    -0.66
     Италијани
    -0.65
     كومونز
    -0.65
    ➟
    -0.65
    POSITIVE LOGITS
     million
    0.31
     mulig
    0.30
    Kjelder
    0.28
     Millionen
    0.26
    instancetype
    0.26
     NSCoder
    0.26
     sintética
    0.26
     due
    0.26
     milliards
    0.26
     whole
    0.24
    Activations Density 0.564%

    No Known Activations