© 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 EvalsExportsAPI 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. 12521
    Prev
    Next
    INDEX
    Explanations

    references to significant updates or improvements in various contexts

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

    following "also"

    np_acts-logits-general · gemini-2.0-flash

    introducing additional information

    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
     anyway
    -0.88
     even
    -0.81
     actually
    -0.76
     justru
    -0.74
     either
    -0.74
    WebServlet
    -0.74
     anyways
    -0.73
    even
    -0.71
     даже
    -0.69
     ACTUALLY
    -0.69
    POSITIVE LOGITS
     וגם
    0.80
    ItemLayout
    0.69
    ."));
    0.63
    ']).
    0.62
    ()].
    0.61
     Италијани
    0.60
    ))));
    0.60
     impressive
    0.59
    ))->
    0.57
    Erreferentziak
    0.56
    Activations Density 0.353%

    No Known Activations