© 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. 10-GEMMASCOPE-RES-16K
    6. 6845
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operations in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.73
    onAttach
    -0.71
    LookAnd
    -0.66
     HasFactory
    -0.66
     BoxFit
    -0.64
    featureID
    -0.61
    Diweddarwch
    -0.60
    Попис
    -0.60
     Italijani
    -0.60
    recated
    -0.59
    POSITIVE LOGITS
     wireType
    0.42
     verrez
    0.35
     Schmer
    0.34
     thermique
    0.34
     nervioso
    0.34
     olvido
    0.33
     pember
    0.33
     Schlag
    0.33
     bolig
    0.33
     AC
    0.32
    Activations Density 1.456%

    No Known Activations