© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 4674
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with objects or entities in code

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

    package names and namespace references in code (particularly Java and C# qualified names like `javax.swing`, `System.Windows.Forms`, `java.util`).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.49
    MessageOf
    -0.47
    readValue
    -0.46
     beginnetje
    -0.46
    GRect
    -0.46
    WriteHeader
    -0.45
    SpringRunner
    -0.44
    NamedQueries
    -0.44
     écoulé
    -0.44
    Хьажоргаш
    -0.43
    POSITIVE LOGITS
     Pingback
    0.53
    󠁢
    0.47
    swing
    0.42
     transfieras
    0.41
     %.
    0.39
    новения
    0.38
    awt
    0.38
     GenerationType
    0.37
    intl
    0.37
     št
    0.37
    Activations Density 0.033%

    No Known Activations