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. 8-GEMMASCOPE-RES-16K
    6. 4775
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and formulas, particularly involving exponents and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gemeinde
    -0.59
    addGroup
    -0.58
     Mondiale
    -0.53
     Parrish
    -0.52
     kecamatan
    -0.51
     العامة
    -0.51
    ivas
    -0.51
     Barbier
    -0.50
    intu
    -0.49
     Bingham
    -0.48
    POSITIVE LOGITS
    enumi
    0.85
    extAlignment
    0.83
     المعيارى
    0.81
    findpost
    0.78
    NUMX
    0.73
    enumii
    0.70
     onAnimation
    0.69
    databind
    0.69
    Autoritní
    0.69
     BoxDecoration
    0.69
    Activations Density 0.707%

    No Known Activations