© 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. 11-GEMMASCOPE-RES-16K
    11. 8276
    Prev
    Next
    INDEX
    Explanations

    references to location and community identifiers in relation to specific counties and townships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁴
    -0.94
     للاسماء
    -0.89
     resourceCulture
    -0.79
    SequentialGroup
    -0.78
    MigrationBuilder
    -0.77
     surla
    -0.75
    CppMethod
    -0.75
    AddTagHelper
    -0.75
    enterOuterAlt
    -0.75
    ⟬
    -0.73
    POSITIVE LOGITS
     jsPsych
    0.45
     intégr
    0.37
     savent
    0.31
     aveug
    0.28
     almendras
    0.26
     kirj
    0.25
    église
    0.25
    belec
    0.25
     knife
    0.24
     Gesichts
    0.24
    Activations Density 0.123%

    No Known Activations