© 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. 12416
    Prev
    Next
    INDEX
    Explanations

    time expressions and temporal indicators

    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
    ésult
    -0.56
     tartalomajánló
    -0.55
     AttributeSet
    -0.55
     Divulgação
    -0.54
    httphttps
    -0.54
    SourceChecksum
    -0.53
     createSlice
    -0.53
     résult
    -0.52
     Geiſt
    -0.49
     InputDecoration
    -0.48
    POSITIVE LOGITS
     noon
    0.77
    Noon
    0.74
     pm
    0.73
     afternoon
    0.71
     Noon
    0.69
    noon
    0.68
     PM
    0.67
     am
    0.65
    pm
    0.63
    PM
    0.63
    Activations Density 0.082%

    No Known Activations