© 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. 20-GEMMASCOPE-RES-16K
    11. 12283
    Prev
    Next
    INDEX
    Explanations

    phrases related to the correct or appropriate selection and use of items or strategies

    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
     largas
    -0.36
     weit
    -0.34
     urma
    -0.34
     mostly
    -0.34
     voeten
    -0.32
     Así
    -0.31
     afge
    -0.31
    ban
    -0.31
     voet
    -0.31
     commonly
    -0.31
    POSITIVE LOGITS
    Appropriate
    0.89
     giusta
    0.88
     appropriate
    0.84
     Appropriate
    0.84
     richtigen
    0.77
     správ
    0.76
    appropriate
    0.75
     wrong
    0.74
     correct
    0.73
     giusti
    0.72
    Activations Density 0.203%

    No Known Activations