© 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. 22-GEMMASCOPE-RES-16K
    6. 13996
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significant events or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saites
    -0.58
     ujednoznacz
    -0.57
    migrationBuilder
    -0.57
     externi
    -0.57
    HostException
    -0.52
     ArrayAdapter
    -0.52
     oprot
    -0.52
    AutoField
    -0.52
    __);
    -0.51
     الحره
    -0.51
    POSITIVE LOGITS
     timing
    0.65
    Timing
    0.54
     Timing
    0.50
     peak
    0.50
     season
    0.49
     seasonal
    0.45
     timings
    0.44
     early
    0.43
     seasons
    0.43
     peaks
    0.42
    Activations Density 0.312%

    No Known Activations