© 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. 13041
    Prev
    Next
    INDEX
    Explanations

    references to garages and doors, particularly in a technical or historical context

    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
    Portale
    -0.65
     Ανακτήθηκε
    -0.63
     purpoſe
    -0.61
    بوابة
    -0.59
    ScopeManager
    -0.59
    Referencies
    -0.59
     houſe
    -0.58
     Efq
    -0.57
     ſta
    -0.57
    Források
    -0.57
    POSITIVE LOGITS
     Humble
    0.82
     humble
    0.81
    humble
    0.80
     garage
    0.76
    Humble
    0.73
     Garage
    0.70
    Garage
    0.66
     Tro
    0.62
    garage
    0.62
     Whip
    0.62
    Activations Density 0.883%

    No Known Activations