© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 10874
    Prev
    Next
    INDEX
    Explanations

    descriptions emphasizing strength and effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nap
    -0.61
    i
    -0.60
    Tween
    -0.60
    e
    -0.59
    Nap
    -0.58
    k
    -0.57
     bribe
    -0.57
    E
    -0.55
    T
    -0.54
     Ski
    -0.54
    POSITIVE LOGITS
    Powerful
    1.92
     Powerful
    1.83
     powerful
    1.81
    powerful
    1.72
     puissant
    1.60
     puissante
    1.56
     poderos
    1.41
     powerfully
    1.41
     poderosa
    1.39
     potente
    1.39
    Activations Density 0.068%

    No Known Activations