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

    Neuronpedia

    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. 1800
    Prev
    Next
    INDEX
    Explanations

    numerical data formats and references typically associated with academic articles

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

    Followed by a parenthesis, preceded by reference information

    np_acts-logits-general · gemini-2.0-flash

    sugar planter

    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
     '\\;'
    -0.77
    OrBuilder
    -0.63
     <>",
    -0.62
     ddelweddau
    -0.61
    quelize
    -0.59
    etcode
    -0.59
    UVEN
    -0.59
    etCode
    -0.57
    ^(@)
    -0.56
    Geografie
    -0.56
    POSITIVE LOGITS
    </thead>
    0.57
    SizeF
    0.47
    Discriminator
    0.46
    цька
    0.46
    ウェル
    0.46
    cetes
    0.45
    joni
    0.42
    objectif
    0.42
    longer
    0.42
    webElementXpaths
    0.42
    Activations Density 0.093%

    No Known Activations