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. 20-GEMMASCOPE-RES-16K
    6. 5088
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to equations

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    SBATCH
    -0.47
    Rüyada
    -0.43
    ネート
    -0.40
    enterOuterAlt
    -0.38
    Ciri
    -0.38
    meralda
    -0.37
    MatInputModule
    -0.37
    cein
    -0.37
     IndexError
    -0.37
    írus
    -0.37
    POSITIVE LOGITS
    intenant
    0.68
     AssemblyCulture
    0.56
     anymore
    0.55
     Audiodateien
    0.54
     novamente
    0.54
     autorytatywna
    0.53
     nuevamente
    0.53
     artık
    0.52
     semula
    0.51
     Revisited
    0.50
    Activations Density 1.158%

    No Known Activations