© 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. 12244
    Prev
    Next
    INDEX
    Explanations

    emotional states and interpersonal relationships

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

    Japanese words followed by particles

    np_acts-logits-general · gemini-2.0-flash

    関係 necessity timing

    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
    SOUNDBITE
    -0.72
    __(/*!
    -0.68
    >--}}
    -0.63
    Géographie
    -0.60
    thâu
    -0.59
    kháu
    -0.59
    migrationBuilder
    -0.58
    SBATCH
    -0.57
    COUVER
    -0.57
    Bakgrunnsstoff
    -0.56
    POSITIVE LOGITS
     है
    0.73
    യാ
    0.72
    であり
    0.68
    이다
    0.66
    である
    0.65
     हैं
    0.61
    udur
    0.58
    임
    0.57
     بوده
    0.56
     hai
    0.54
    Activations Density 0.060%

    No Known Activations