© 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. 34-GEMMASCOPE-RES-16K
    11. 10930
    Prev
    Next
    INDEX
    Explanations

    numerical data related to measurements and concentrations in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PyTuple
    -0.50
     étoit
    -0.48
    
    -0.46
    ∋
    -0.46
     Administrativna
    -0.46
    nodoc
    -0.45
    asteroide
    -0.44
     pouvoit
    -0.44
     صوتيه
    -0.42
     kilowatt
    -0.42
    POSITIVE LOGITS
    tonode
    0.53
    initializeApp
    0.42
    unzel
    0.41
    setupUi
    0.41
    beginTransaction
    0.37
    SequentialGroup
    0.37
    PositiveButton
    0.37
    usitis
    0.35
     sin
    0.35
    writeField
    0.35
    Activations Density 0.940%

    No Known Activations