© 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. 22-GEMMASCOPE-RES-16K
    11. 8557
    Prev
    Next
    INDEX
    Explanations

    themes related to existential crises and identity struggles

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

    after "the" or "and"

    np_acts-logits-general · gemini-2.0-flash

    mystical path and admiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colère
    -0.67
     rédaction
    -0.65
     réputation
    -0.64
     bisous
    -0.62
     amitié
    -0.60
     foncé
    -0.60
     décision
    -0.58
     decisione
    -0.58
     giù
    -0.57
     endroits
    -0.57
    POSITIVE LOGITS
     hero
    0.70
     myth
    0.69
    hero
    0.67
     sublimation
    0.65
     tragic
    0.62
     subli
    0.61
     heroic
    0.61
    myth
    0.61
     fantasy
    0.59
     ideal
    0.59
    Activations Density 0.384%

    No Known Activations