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. 10-GEMMASCOPE-RES-16K
    6. 12588
    Prev
    Next
    INDEX
    Explanations

    phrases related to sporting events and match predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    काल
    -0.48
     kony
    -0.46
    iet
    -0.46
    الحياه
    -0.45
    OnAdd
    -0.45
    ArrowToggle
    -0.45
     getView
    -0.44
    camin
    -0.44
    tiens
    -0.44
    ContentAlignment
    -0.43
    POSITIVE LOGITS
     disponibilités
    0.77
     game
    0.72
     estekak
    0.70
    AndEndTag
    0.69
     CURIAM
    0.66
     AssemblyProduct
    0.65
    IUrlHelper
    0.64
    LookAnd
    0.64
    __':
    
    0.64
     match
    0.63
    Activations Density 0.183%

    No Known Activations