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. 10111
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements related to types and their validations

    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
     purpoſe
    -0.92
     fubject
    -0.80
    ſelf
    -0.80
    setVerticalGroup
    -0.80
     Jefus
    -0.79
     beſt
    -0.78
     cauſe
    -0.78
     Majefty
    -0.78
     myſelf
    -0.77
     viſ
    -0.77
    POSITIVE LOGITS
     values
    0.90
     value
    0.77
     AssemblyCulture
    0.76
    values
    0.75
    value
    0.75
     Values
    0.70
     getValue
    0.67
    Values
    0.67
     değer
    0.64
     VALUES
    0.63
    Activations Density 0.185%

    No Known Activations