© 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. 24-GEMMASCOPE-RES-16K
    11. 2553
    Prev
    Next
    INDEX
    Explanations

    elements related to medical terms and conditions

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

    Numbers followed by delimiters (".", ",", "1")

    np_acts-logits-general · gemini-2.0-flash

    numbers after punctuation or operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    اهم
    -0.45
    <eos>
    -0.43
     technical
    -0.42
     war
    -0.42
     gel
    -0.42
    Roy
    -0.41
    落下
    -0.41
    üler
    -0.41
     resident
    -0.40
    𝐗
    -0.40
    POSITIVE LOGITS
     متعلقه
    1.13
    tagHelperRunner
    0.97
     StatefulWidget
    0.83
    ConstraintMaker
    0.79
    }{*}{
    0.79
    IsMutable
    0.79
     disambiguazione
    0.77
    XmlAccessType
    0.75
     Процитовано
    0.75
     مرئيه
    0.74
    Activations Density 0.540%

    No Known Activations