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. 2-GEMMASCOPE-RES-16K
    6. 4896
    Prev
    Next
    INDEX
    Explanations

    terms related to sports fixtures 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 @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ńczy
    -0.53
    θει
    -0.53
    expandindo
    -0.53
     Baudelaire
    -0.53
    +#+
    -0.52
     NSCoder
    -0.52
     voelt
    -0.51
     MemoryStream
    -0.51
     mergeFrom
    -0.50
    gevens
    -0.50
    POSITIVE LOGITS
     clash
    1.11
     matchup
    1.01
     clashes
    0.98
     clashed
    0.93
    clash
    0.91
     matchups
    0.90
     showdown
    0.89
     Clash
    0.88
     rivalry
    0.85
    Clash
    0.83
    Activations Density 0.248%

    No Known Activations