© 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. 22-GEMMASCOPE-RES-16K
    11. 8288
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to magical abilities and technology

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

    Glowing, magical transformations and appearances

    np_acts-logits-general · gemini-2.0-flash

    glowing, appearing, magically forming

    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
    basicConfig
    -0.50
     sauvages
    -0.47
     fréqu
    -0.47
    CORD
    -0.46
    الإنجليزية
    -0.45
     gön
    -0.44
     fréquemment
    -0.43
    Early
    -0.43
     permissive
    -0.42
     faciles
    -0.42
    POSITIVE LOGITS
     magically
    0.90
     forming
    0.89
     floating
    0.86
     formed
    0.84
     glowing
    0.84
     levit
    0.83
     Formation
    0.77
     formation
    0.76
     emitting
    0.76
     instantly
    0.75
    Activations Density 0.399%

    No Known Activations