© 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. 8-GEMMASCOPE-RES-16K
    6. 11025
    Prev
    Next
    INDEX
    Explanations

    the degree of sufficiency or excess in quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     starb
    -0.62
    /**
    -0.61
     condizioni
    -0.61
    RectangleBorder
    -0.57
     mellitus
    -0.55
    impulan
    -0.53
    herren
    -0.53
     متعلقه
    -0.53
     veder
    -0.53
     éte
    -0.53
    POSITIVE LOGITS
     amount
    1.09
    więcej
    1.04
     amounts
    0.90
    amount
    0.88
     additional
    0.86
     lots
    0.84
     ilości
    0.83
     extra
    0.83
     enough
    0.83
    Mucha
    0.82
    Activations Density 0.343%

    No Known Activations