© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 67931
    Prev
    Next
    INDEX
    Explanations

    terms related to generated content or files

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

    generated text or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iprot
    -0.53
    yargs
    -0.46
    layoutControl
    -0.42
    fortawesome
    -0.40
     mergeFrom
    -0.40
    mimetype
    -0.40
     RoutedEventArgs
    -0.39
    IntentFilter
    -0.39
    tabControl
    -0.39
    stück
    -0.37
    POSITIVE LOGITS
    Generated
    3.78
     Generated
    2.16
    generated
    1.63
    GENERATED
    1.62
     generated
    1.45
     GENERATED
    1.36
    GeneratedCode
    1.16
    生成的
    1.11
    enerated
    1.09
    Generating
    1.05
    Activations Density 0.001%

    No Known Activations