© 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-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 7737
    Prev
    Next
    INDEX
    Explanations

    repeated references to features in a technical or software context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    audiovisuel
    -0.48
    цездатний
    -0.45
    曖昧さ回避
    -0.45
     Traditionally
    -0.44
    awtextra
    -0.44
    homonymie
    -0.43
     traditionally
    -0.43
    Personendaten
    -0.42
    XmlType
    -0.42
     tradizione
    -0.42
    POSITIVE LOGITS
     features
    2.78
    features
    2.59
     Features
    2.56
    Features
    2.45
     feature
    2.34
     FEATURES
    2.28
     Feature
    2.23
    feature
    2.20
    Feature
    2.14
    FEATURES
    2.13
    Activations Density 0.244%

    No Known Activations