© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 8139
    Prev
    Next
    INDEX
    Explanations

    emotional and subjective reactions to social or political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Emotion Validation

    No Comments

    Negative Logits
    StoryboardSegue
    -0.65
    :])
    -0.54
    stination
    -0.54
    楔
    -0.53
     Administrativna
    -0.53
     kiệm
    -0.52
     مؤرشف
    -0.51
     dependencia
    -0.50
     Laur
    -0.50
    ()?;
    -0.49
    POSITIVE LOGITS
     upset
    1.08
     annoyed
    0.98
     displeased
    0.95
     disturbed
    0.94
     disappointed
    0.93
     frustrated
    0.92
     angered
    0.92
     irritated
    0.92
     outraged
    0.92
     furious
    0.91
    Activations Density 0.283%

    No Known Activations