© 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. 9996
    Prev
    Next
    INDEX
    Explanations

    hyperlinks and anchor tags in HTML content

    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
    tvguidetime
    -1.25
     itſelf
    -1.19
    GEBURTSDATUM
    -1.15
     purpoſe
    -1.11
     pleaſure
    -1.10
     Monfieur
    -1.09
     Theſe
    -1.08
     ſtate
    -1.08
    ſelf
    -1.06
    abestanden
    -1.06
    POSITIVE LOGITS
    a
    1.18
     href
    0.98
     link
    0.83
    Link
    0.82
    NavLink
    0.79
     Link
    0.79
    href
    0.77
    link
    0.73
     to
    0.72
    i
    0.70
    Activations Density 0.070%

    No Known Activations