© 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. 1-GEMMASCOPE-RES-16K
    6. 8978
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "pass" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.59
     deb
    -0.49
     initComponents
    -0.49
    debut
    -0.48
     Debut
    -0.47
    Circum
    -0.46
     debu
    -0.45
     Deb
    -0.45
     debut
    -0.44
     circumstance
    -0.44
    POSITIVE LOGITS
    pass
    0.60
     trauma
    0.59
     traum
    0.54
     traumatic
    0.51
    pexpr
    0.49
     killer
    0.49
     pass
    0.47
     funcionales
    0.47
     Killer
    0.47
    trauma
    0.47
    Activations Density 0.206%

    No Known Activations