Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14528
    Prev
    Next
    INDEX
    Explanations

    expressions of emotions, particularly feelings of guilt and sorrow

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

    Expressing feelings or emotions

    np_acts-logits-general · gemini-2.0-flash

    subjective feelings or opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Zeneca
    -0.68
    labus
    -0.58
     Autorizaciones
    -0.56
     RISERVATA
    -0.56
    anians
    -0.55
    FunctionFlags
    -0.55
     otomatig
    -0.54
    例文帳に追加
    -0.53
    izzazioni
    -0.53
    Havolalar
    -0.53
    POSITIVE LOGITS
     like
    0.76
     comfortable
    0.72
    Felt
    0.69
     secure
    0.65
     compelled
    0.63
    Feels
    0.62
     safe
    0.61
    secure
    0.60
     Felt
    0.59
     felt
    0.59
    Activations Density 0.076%

    No Known Activations