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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3561
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and their properties, specifically related to derivatives and integration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.46
    strut
    -0.45
    ::_('
    -0.40
    )\}$
    -0.39
     Bulldogs
    -0.38
    usammen
    -0.38
    zzleHttp
    -0.37
    colli
    -0.37
     Roads
    -0.36
    cillos
    -0.36
    POSITIVE LOGITS
    interopRequire
    0.56
    atguigu
    0.52
    rungsseite
    0.48
     camicia
    0.47
    makeText
    0.44
     referrerpolicy
    0.43
    gameserver
    0.42
    AddTagHelper
    0.41
    KommentareTeilen
    0.41
     aard
    0.40
    Activations Density 2.635%

    No Known Activations