Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 10266
    Prev
    Next
    INDEX
    Explanations

    instances of the word "half" and its variations in numerical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -0.84
    UpInside
    -0.81
    Bibliographie
    -0.69
    مصادر
    -0.68
    ://"
    -0.68
     tems
    -0.67
    ="#"><
    -0.65
    Reactivity
    -0.65
    cues
    -0.65
    enseignements
    -0.64
    POSITIVE LOGITS
     half
    3.47
     Half
    3.16
    Half
    3.14
    half
    3.13
     HALF
    2.96
    HALF
    2.65
     halves
    2.41
    半
    1.99
     setengah
    1.98
     halv
    1.97
    Activations Density 0.049%

    No Known Activations