© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11459
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and programming constructs related to computations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FXMLLoader
    -0.74
    JsonHelper
    -0.64
    CodedInputStream
    -0.60
    inguém
    -0.57
    Izvori
    -0.55
     protoimpl
    -0.54
     JAXBElement
    -0.52
    }-*/;
    -0.51
     Tess
    -0.51
    ℗
    -0.51
    POSITIVE LOGITS
    tvguidetime
    0.88
    enumi
    0.73
     وتسجيلات
    0.65
    </thead>
    0.62
    Autoritní
    0.62
     autorytatywna
    0.61
    =
    0.61
     للاسماء
    0.59
    riwal
    0.58
    nesty
    0.58
    Activations Density 0.011%

    No Known Activations