© 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. 24-GEMMASCOPE-RES-16K
    6. 7955
    Prev
    Next
    INDEX
    Explanations

    questions about feelings and self-reflection

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

    Pronouns followed by "feel"

    np_acts-logits-general · gemini-2.0-flash

    feeling or being felt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Emotion Validation

    No Comments

    Negative Logits
     متعلقه
    -0.71
     समीक्षक
    -0.61
    ########.
    -0.60
    WebElementEntity
    -0.57
    енча
    -0.56
     lanjut
    -0.55
    addCriterion
    -0.53
    MENAFN
    -0.53
    weetened
    -0.52
     BrowserModule
    -0.52
    POSITIVE LOGITS
     feel
    3.29
     feels
    3.01
     feeling
    2.99
    Feel
    2.89
    feel
    2.88
     Feel
    2.86
     felt
    2.80
     FEEL
    2.64
     Feeling
    2.61
    feeling
    2.59
    Activations Density 0.190%

    No Known Activations