© 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. 24-GEMMASCOPE-RES-16K
    11. 5573
    Prev
    Next
    INDEX
    Explanations

    technical terms and numerical values related to data transfer limits and simulation parameters

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

    preceding "to" implying intention or requirement

    np_acts-logits-general · gemini-2.0-flash

    achieving a desired state

    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
     ProtoMessage
    -0.69
     propOrder
    -0.63
    ]")]
    -0.63
    */].
    -0.62
    
    -0.60
    TagMode
    -0.60
    AndroidJUnit
    -0.56
    IndentedString
    -0.56
    rungsseite
    -0.56
     GIPHY
    -0.56
    POSITIVE LOGITS
     desired
    0.66
     target
    0.56
    desired
    0.54
     Desired
    0.52
     targets
    0.52
     gewüns
    0.52
     goal
    0.50
     balance
    0.50
     ensure
    0.47
     maintain
    0.47
    Activations Density 1.053%

    No Known Activations