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. 8-GEMMASCOPE-RES-16K
    6. 21
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and software components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.70
     vPvB
    -0.66
    endphp
    -0.65
     nahilalakip
    -0.59
     surla
    -0.58
     numberWith
    -0.58
    #
    -0.57
     unknownFields
    -0.56
     ſehr
    -0.56
    nthetic
    -0.55
    POSITIVE LOGITS
    contentLoaded
    0.39
     виправивши
    0.35
     podamos
    0.33
    InstrumentedTest
    0.32
    Obrázky
    0.31
    FormTagHelper
    0.31
    JspWriter
    0.30
     Fenster
    0.29
     ningún
    0.29
     error
    0.29
    Activations Density 0.153%

    No Known Activations