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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3932
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical discussions or generalizations about groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.59
    PointSize
    -0.57
     assic
    -0.56
    MigrationBuilder
    -0.56
    prüche
    -0.56
     taxes
    -0.55
    Aws
    -0.55
     Allahabad
    -0.54
    letus
    -0.54
     judiciales
    -0.54
    POSITIVE LOGITS
     many
    0.86
    Many
    0.80
    MANY
    0.80
     Many
    0.80
    many
    0.79
     vieler
    0.77
    MLLoader
    0.75
    ногие
    0.74
     muchas
    0.72
     بسیاری
    0.72
    Activations Density 0.202%

    No Known Activations