© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 1236
    Prev
    Next
    INDEX
    Explanations

    mechanical devices and components related to connecting or attaching

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

    connected or installed into a location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    interopRequire
    -0.52
    LookAnd
    -0.42
    ViewImports
    -0.41
    CreateModel
    -0.40
    formik
    -0.40
     stesse
    -0.38
     rootReducer
    -0.38
    日閲覧
    -0.37
    gaged
    -0.36
    getLogger
    -0.36
    POSITIVE LOGITS
     defaultstate
    0.54
     install
    0.51
     irgendwo
    0.50
    yntaxException
    0.49
     anywhere
    0.47
     wherever
    0.47
     installation
    0.46
    ۜ
    0.45
     easy
    0.44
     installed
    0.44
    Activations Density 0.048%

    No Known Activations