© 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. 2-GEMMASCOPE-RES-16K
    11. 3923
    Prev
    Next
    INDEX
    Explanations

    positive evaluations or descriptors often indicating excellence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputBorder
    -0.91
     Thesaurus
    -0.63
     État
    -0.62
    oole
    -0.62
     Bartholo
    -0.61
     kysy
    -0.61
    URIComponent
    -0.61
     väh
    -0.61
    enderror
    -0.61
     Mindanao
    -0.60
    POSITIVE LOGITS
     genius
    0.70
    :])
    0.64
     BaseActivity
    0.64
     brilliant
    0.61
     geniuses
    0.61
    genius
    0.60
     LiveData
    0.60
    Brilliant
    0.59
     Genius
    0.59
     dresses
    0.58
    Activations Density 0.054%

    No Known Activations