© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 6688
    Prev
    Next
    INDEX
    Explanations

    discussions around the experiences and challenges of being a single parent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档于
    -0.58
    ✭✭
    -0.53
    VARD
    -0.50
    crites
    -0.49
     [{
    -0.49
    êmio
    -0.48
    Biographies
    -0.47
     مشارکت‌کنندگان
    -0.45
    ynb
    -0.44
    __':
    -0.44
    POSITIVE LOGITS
     yourself
    0.71
    Referencie
    0.65
    AllowUser
    0.61
    如果你
    0.59
     anyone
    0.57
     cualquiera
    0.57
     незавершена
    0.56
    marvin
    0.56
    yourself
    0.55
     समीक्षाओं
    0.54
    Activations Density 0.205%

    No Known Activations