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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14482
    Prev
    Next
    INDEX
    Explanations

    instances of expressions and phrases that suggest interpretation or opinion

    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
    IUrlHelper
    -0.73
    DockStyle
    -0.63
    AddTagHelper
    -0.63
     للاسماء
    -0.62
     propOrder
    -0.60
     autorytatywna
    -0.60
     InputDecoration
    -0.60
    Autoritní
    -0.57
    SharedDtor
    -0.56
     ***!
    -0.55
    POSITIVE LOGITS
    cln
    0.35
     airbags
    0.35
    而言
    0.33
    padded
    0.33
    boards
    0.31
     radiators
    0.31
    bridges
    0.31
     Foley
    0.30
    balls
    0.30
     Ponds
    0.30
    Activations Density 0.692%

    No Known Activations