© 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. 3-GEMMASCOPE-RES-16K
    11. 5474
    Prev
    Next
    INDEX
    Explanations

    terms related to measurement and assessment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.51
    
    -0.45
    spesies
    -0.44
     ModelExpression
    -0.44
     Bioaccumulative
    -0.43
    optionalTypeArgs
    -0.42
    uthorized
    -0.42
    batross
    -0.40
    enerbahçe
    -0.40
     jsonify
    -0.40
    POSITIVE LOGITS
     MB
    0.56
    mb
    0.54
     Muhammad
    0.53
    ########.
    0.52
     Mohammed
    0.50
     mb
    0.48
     thy
    0.47
     <!--
    0.47
    ded
    0.46
     cow
    0.46
    Activations Density 1.327%

    No Known Activations