© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9323
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the substring "ba" along with variations in capitalization

    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
     Wheeler
    -0.57
     roche
    -0.57
     فريبيس
    -0.56
     hik
    -0.56
    brando
    -0.56
     Cré
    -0.56
     Wilson
    -0.56
    ρή
    -0.55
    ───
    -0.55
     Brun
    -0.55
    POSITIVE LOGITS
    Ba
    2.79
     Ba
    2.77
    ba
    2.58
     ba
    2.56
    BA
    2.31
     BA
    2.28
     Baf
    1.53
     Baumann
    1.53
     Baer
    1.46
     baffle
    1.45
    Activations Density 0.078%

    No Known Activations