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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120756
    Prev
    Next
    INDEX
    Explanations

    conventional formats of addresses and locations

    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
     myſelf
    -0.52
     juſ
    -0.49
    iostream
    -0.47
     himſelf
    -0.47
     ſch
    -0.46
    ſelves
    -0.45
     viſ
    -0.45
    Geplaatst
    -0.45
     cauſe
    -0.45
     Houſe
    -0.44
    POSITIVE LOGITS
    GEBURTS
    0.60
    awtextra
    0.57
     which
    0.56
     engraçadas
    0.53
    @",
    0.52
    ,<
    0.47
     direta
    0.47
     ،
    0.47
     tearDown
    0.46
     comerciais
    0.46
    Activations Density 0.080%

    No Known Activations