© 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. 18-GEMMASCOPE-RES-16K
    11. 1811
    Prev
    Next
    INDEX
    Explanations

    elements related to character development in narratives

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

    Characters who are abandoned/orphaned

    np_acts-logits-general · gemini-2.0-flash

    orphaned, homeless, or wandering state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overkill
    -0.52
     censorship
    -0.50
     Wordle
    -0.47
     Satisfied
    -0.45
     censor
    -0.44
    reiches
    -0.44
    Satisfied
    -0.44
     cancellations
    -0.43
     feedback
    -0.43
    qtype
    -0.43
    POSITIVE LOGITS
     orphaned
    0.88
     wandering
    0.84
     befri
    0.83
     orphan
    0.80
     abandoned
    0.79
    orphaned
    0.79
     adopted
    0.78
     wander
    0.77
     rescued
    0.77
     homeless
    0.76
    Activations Density 0.362%

    No Known Activations