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. 4-GEMMASCOPE-RES-16K
    6. 3598
    Prev
    Next
    INDEX
    Explanations

    references to specific legal cases and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Steck
    -0.75
     aveug
    -0.74
     blocs
    -0.67
     Exacts
    -0.67
     becauſe
    -0.67
     Gerais
    -0.66
     sensibilité
    -0.66
     boycot
    -0.66
     spoko
    -0.66
     Calvo
    -0.65
    POSITIVE LOGITS
     BAK
    0.79
    UserScript
    0.71
     Mooney
    0.71
    orghini
    0.69
     بيها
    0.68
     незавершена
    0.68
     hull
    0.67
     BoxDecoration
    0.65
    ENTRE
    0.65
    Dsl
    0.65
    Activations Density 7.455%

    No Known Activations