© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13834
    Prev
    Next
    INDEX
    Explanations

    elements related to user input fields and interface components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.85
    참고
    -0.70
    __*/
    -0.69
    enumii
    -0.68
    fjspx
    -0.62
    
    -0.62
     CreateTagHelper
    -0.60
     BoxFit
    -0.60
     propOrder
    -0.59
    oneofs
    -0.58
    POSITIVE LOGITS
     purpoſe
    0.38
    ">—
    0.34
     pleaſure
    0.34
    drawSprites
    0.34
     кӀ
    0.32
    Instrumented
    0.31
     plais
    0.31
     yourselves
    0.31
     Exist
    0.31
    Exist
    0.30
    Activations Density 0.210%

    No Known Activations