© 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. 14-GEMMASCOPE-RES-16K
    6. 8978
    Prev
    Next
    INDEX
    Explanations

    specific character sequences and symbols, particularly from non-English scripts and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.88
    Tikang
    -0.88
    Portály
    -0.82
    parsedMessage
    -0.81
     AssemblyCulture
    -0.79
    Personendaten
    -0.79
    setVerticalGroup
    -0.76
    GeoNames
    -0.75
    AsUp
    -0.73
    EDEFAULT
    -0.70
    POSITIVE LOGITS
     F
    0.60
     Sp
    0.59
     מ
    0.57
     b
    0.56
     K
    0.56
     T
    0.56
     अ
    0.56
     P
    0.55
     A
    0.55
     प
    0.55
    Activations Density 0.078%

    No Known Activations