© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 3537
    Prev
    Next
    INDEX
    Explanations

    references to personal feelings and opinions, particularly about relationships and judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Opinions, attitudes, and feelings

    np_acts-logits-general · gemini-2.0-flash

    someone's opinion or feeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ::$_
    -0.57
    invokeLater
    -0.55
    cshtml
    -0.54
     nahilalakip
    -0.53
    ///</
    -0.53
     ostavi
    -0.52
     Мексичка
    -0.51
    tisgarh
    -0.50
    dija
    -0.49
    auta
    -0.49
    POSITIVE LOGITS
     regarding
    1.47
     about
    1.46
     concerning
    1.34
     Regarding
    1.18
     riguardo
    1.18
    regarding
    1.14
    Regarding
    1.13
    about
    1.12
     kuhusu
    1.08
     щодо
    1.08
    Activations Density 0.446%

    No Known Activations