© 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. 887
    Prev
    Next
    INDEX
    Explanations

    instances of self-reference or expressions of personal opinion

    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
     jsPsych
    -0.50
    WebVitals
    -0.48
    دانشنامهٔ
    -0.48
     ligiloj
    -0.47
     AssemblyVersion
    -0.45
     miniaturka
    -0.44
     <>",
    -0.43
     besluit
    -0.43
    genodigd
    -0.42
     căr
    -0.42
    POSITIVE LOGITS
     personally
    0.56
     seriously
    0.55
     sincerely
    0.53
     fully
    0.52
     fail
    0.50
     serious
    0.49
    Seriously
    0.49
     guarantee
    0.48
     firmly
    0.48
     Seriously
    0.47
    Activations Density 0.275%

    No Known Activations