© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 4383
    Prev
    Next
    INDEX
    Explanations

    specific instance-based contexts and examples in technical or explanatory texts

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

    an illustration or instance is given

    np_acts-logits-general · gemini-2.0-flash

    illustrative examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.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
    TProtocol
    -0.49
    tagHelperRunner
    -0.47
    AutoModerator
    -0.45
    
    -0.45
     BrowserModule
    -0.44
    istoitu
    -0.44
    httphttps
    -0.42
    tagHelper
    -0.42
    IsMutable
    -0.42
    StructEnd
    -0.42
    POSITIVE LOGITS
    Specifically
    0.62
     chiefly
    0.60
     mainly
    0.59
     particularly
    0.59
     principally
    0.58
     primarily
    0.57
     Mainly
    0.57
    Mainly
    0.56
    specifically
    0.55
     principalement
    0.55
    Activations Density 0.772%

    No Known Activations