© 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. 5249
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "sign" and its variations

    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
    Diweddarwch
    -0.41
     suspect
    -0.38
    awaiter
    -0.37
    kháu
    -0.37
     situazione
    -0.37
    Aholisi
    -0.36
     sinar
    -0.36
    signs
    -0.35
     урна
    -0.35
    ändig
    -0.35
    POSITIVE LOGITS
    atories
    0.77
    ificantly
    0.59
    ifier
    0.57
    posting
    0.57
    posts
    0.56
    ATURES
    0.56
    ificance
    0.56
    iture
    0.54
    itures
    0.52
     الحره
    0.51
    Activations Density 0.224%

    No Known Activations