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. 11481
    Prev
    Next
    INDEX
    Explanations

    phrases and references to fractions, particularly "half"

    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
     kasarigan
    -0.55
    >//
    -0.44
    日閲覧
    -0.44
    AndroidJUnit
    -0.42
     Codable
    -0.42
    SerializedSize
    -0.40
    forName
    -0.40
    @[+][
    -0.40
     StyleSheet
    -0.39
     cuivre
    -0.39
    POSITIVE LOGITS
    Half
    1.20
     Half
    1.16
    half
    1.15
     half
    1.13
     HALF
    1.09
    HALF
    0.97
     metade
    0.86
     halves
    0.86
     Hälfte
    0.86
    一半
    0.80
    Activations Density 0.208%

    No Known Activations