© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 10668
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions about character motivations and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.93
    رشف
    -0.91
     MainAxisSize
    -0.90
    AnchorStyles
    -0.90
     utafitiHapana
    -0.85
    GEBURTSDATUM
    -0.79
    Composable
    -0.79
    parsedMessage
    -0.77
    afficheront
    -0.75
    yntaxException
    -0.74
    POSITIVE LOGITS
     what
    0.37
     lots
    0.33
     mucha
    0.32
     nothing
    0.32
     doing
    0.31
     because
    0.31
     ledit
    0.30
     ciò
    0.30
    mentioned
    0.30
     many
    0.29
    Activations Density 2.054%

    No Known Activations