Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12426
    Prev
    Next
    INDEX
    Explanations

    references to specific researchers and their contributions in scientific literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.64
    fjspx
    -0.58
     незавершена
    -0.54
     autorytatywna
    -0.50
    ніципалі
    -0.49
    __*/
    -0.47
     Bewußt
    -0.46
     للاسماء
    -0.46
    ondissement
    -0.45
     للمعارف
    -0.44
    POSITIVE LOGITS
    uno
    0.48
    typeorm
    0.44
     report
    0.43
     et
    0.41
     Envelope
    0.41
    ison
    0.41
    qvarna
    0.40
    yon
    0.40
    kal
    0.40
    ener
    0.40
    Activations Density 0.543%

    No Known Activations