© 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. 13572
    Prev
    Next
    INDEX
    Explanations

    patterns related to numeric references and code syntax

    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
    RetentionPolicy
    -0.76
    rungsseite
    -0.69
    XmlType
    -0.64
     protoimpl
    -0.58
    createCanvas
    -0.58
    QApplication
    -0.57
    Cubit
    -0.56
    verwijspagina
    -0.56
    }^{+\
    -0.55
    Ingress
    -0.55
    POSITIVE LOGITS
    Captor
    0.47
    forName
    0.44
     nữa
    0.43
     payé
    0.41
    ன்ற
    0.41
    ății
    0.41
     uLocal
    0.40
     County
    0.40
    gever
    0.39
     autorisés
    0.39
    Activations Density 0.986%

    No Known Activations