© 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. 12-GEMMASCOPE-RES-16K
    11. 15425
    Prev
    Next
    INDEX
    Explanations

    instances of conditional phrases and expressions of uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maternidade
    -0.49
     huéspedes
    -0.49
     pères
    -0.49
    babkan
    -0.49
     Überras
    -0.47
     frühen
    -0.46
     tė
    -0.45
     pérd
    -0.44
     darbu
    -0.44
     satisfecho
    -0.44
    POSITIVE LOGITS
     iParam
    0.54
     ModelExpression
    0.47
     PT
    0.46
     nullptr
    0.42
     PD
    0.41
     GI
    0.41
     MDL
    0.40
    featureID
    0.40
     PI
    0.40
    migrationBuilder
    0.40
    Activations Density 0.307%

    No Known Activations