© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 12830
    Prev
    Next
    INDEX
    Explanations

    references to sports achievements and competitions, particularly those involving relay races and doubles events

    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
    !("{}",
    -0.64
    setupUi
    -0.60
    Datuak
    -0.56
    Портал
    -0.53
    ApiModelProperty
    -0.51
    Osob
    -0.50
     peix
    -0.50
    CurrentValue
    -0.49
    offering
    -0.49
    endwhile
    -0.48
    POSITIVE LOGITS
     team
    0.89
     teams
    0.81
    team
    0.75
     AssemblyCulture
    0.70
    Team
    0.67
     Team
    0.66
     équipe
    0.65
     formation
    0.64
    teams
    0.63
     AssemblyVersion
    0.61
    Activations Density 0.666%

    No Known Activations