© 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. 41-GEMMASCOPE-RES-16K
    6. 6951
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate time or sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Autorisations
    -0.78
    uxxxx
    -0.70
     Infórmanos
    -0.69
     feroit
    -0.66
    ingly
    -0.66
    
    -0.66
    InjectAttribute
    -0.65
     дописавши
    -0.64
    setVerticalGroup
    -0.64
    actéristi
    -0.63
    POSITIVE LOGITS
     other
    0.34
     view
    0.33
     whole
    0.33
     sole
    0.32
     very
    0.32
     latter
    0.32
     year
    0.31
     life
    0.31
     entire
    0.30
     immediate
    0.30
    Activations Density 0.227%

    No Known Activations