© 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. 40-GEMMASCOPE-RES-16K
    6. 5188
    Prev
    Next
    INDEX
    Explanations

    references to "old" and "old-fashioned" concepts, places, or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     older
    -0.53
    older
    -0.50
     otherwise
    -0.49
     old
    -0.49
     sonst
    -0.45
     Older
    -0.44
    old
    -0.43
    umerable
    -0.43
    otherwise
    -0.42
     linkovi
    -0.42
    POSITIVE LOGITS
     fashioned
    1.22
    fashioned
    1.09
    school
    0.83
     timers
    0.79
    timers
    0.75
     skool
    0.73
    timer
    0.70
    Fashion
    0.70
     Fashion
    0.65
     timer
    0.65
    Activations Density 0.190%

    No Known Activations