© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 3146
    Prev
    Next
    INDEX
    Explanations

    temporal indicators that denote events or actions occurring in a specified timeframe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -0.67
     against
    -0.63
     when
    -0.63
     after
    -0.62
     according
    -0.60
     in
    -0.59
     from
    -0.59
     while
    -0.59
     for
    -0.59
     during
    -0.59
    POSITIVE LOGITS
     Through
    1.66
     Along
    1.63
     Within
    1.63
    Through
    1.63
     Throughout
    1.60
     During
    1.59
     Between
    1.59
     Upon
    1.58
     Among
    1.55
    Within
    1.55
    Activations Density 0.725%

    No Known Activations