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. 7313
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal statements or judicial proceedings

    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
     المعيارى
    -0.43
     Weih
    -0.39
    Slf
    -0.38
    ongiorno
    -0.38
    öfe
    -0.36
    VIAF
    -0.36
    ImgUrl
    -0.35
     Utara
    -0.34
     данных
    -0.34
    CardNumber
    -0.34
    POSITIVE LOGITS
     propOrder
    0.60
     resourceCulture
    0.59
    interopRequire
    0.57
     يتيمه
    0.50
     esternos
    0.50
    BufferException
    0.49
    windowFixed
    0.45
    verwijspagina
    0.45
    PostInfinity
    0.45
    AutoField
    0.44
    Activations Density 3.652%

    No Known Activations