© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 11350
    Prev
    Next
    INDEX
    Explanations

    phrases and sentiments related to reputation and public perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.66
    GOTREF
    -0.61
    JKLM
    -0.58
     viewType
    -0.57
    tdessen
    -0.56
    ::::::::
    -0.55
    onOptions
    -0.53
    NoSuchAlgorithm
    -0.52
    pegno
    -0.49
    arka
    -0.48
    POSITIVE LOGITS
     certainly
    3.06
     definitely
    2.90
    certainly
    2.61
     surely
    2.56
     Certainly
    2.54
     undoubtedly
    2.50
    Certainly
    2.46
     obviously
    2.43
    definitely
    2.37
    Definitely
    2.31
    Activations Density 0.579%

    No Known Activations