© 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. 18-GEMMASCOPE-RES-16K
    11. 12360
    Prev
    Next
    INDEX
    Explanations

    the presence of relationships and classifications within data and texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by tables/examples/characteristics

    np_acts-logits-general · gemini-2.0-flash

    characteristics of multiple items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     einem
    -0.64
     eine
    -0.64
     unui
    -0.64
     someone
    -0.63
     a
    -0.62
     Someone
    -0.62
     Seorang
    -0.61
     something
    -0.61
    einem
    -0.61
    Someone
    -0.59
    POSITIVE LOGITS
     these
    1.32
     các
    1.10
     those
    1.10
    these
    1.08
     poszczegól
    1.06
     each
    1.01
    those
    0.93
     jednotliv
    0.93
    These
    0.87
     των
    0.87
    Activations Density 0.990%

    No Known Activations