© 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. 3-GEMMASCOPE-RES-16K
    6. 11817
    Prev
    Next
    INDEX
    Explanations

    references to groups or classifications, particularly in terms of "los" and "os"

    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
    -0.75
     pouvoirs
    -0.65
     Poincaré
    -0.63
    вної
    -0.63
     Estadual
    -0.63
     gouvernements
    -0.62
     vecka
    -0.61
     functor
    -0.61
     anvil
    -0.59
     varandra
    -0.59
    POSITIVE LOGITS
     los
    1.08
     οι
    1.00
     dels
    0.95
     mga
    0.95
    Οι
    0.94
     των
    0.93
     les
    0.92
     pinulongan
    0.88
     those
    0.84
     các
    0.82
    Activations Density 0.034%

    No Known Activations