© 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. 3-GEMMASCOPE-RES-16K
    11. 5895
    Prev
    Next
    INDEX
    Explanations

    the word "vast" and variations indicating a large or significant quantity

    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
    edu
    -0.64
    else
    -0.64
     Snowden
    -0.61
    eu
    -0.60
    </b>
    -0.57
    emergency
    -0.56
    derry
    -0.56
     Lorena
    -0.55
     ogn
    -0.55
     followed
    -0.55
    POSITIVE LOGITS
     vast
    2.36
     Vast
    2.14
    Vast
    2.07
    vast
    2.02
     vasto
    1.17
     vastly
    1.02
     majority
    1.00
     vaste
    0.95
     overwhelming
    0.94
    :✨
    0.94
    Activations Density 0.070%

    No Known Activations