© 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. 6326
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to modeling and analysis in scientific contexts

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

    "model" followed by other tokens

    np_acts-logits-general · gemini-2.0-flash

    model, models, or its foreign variants

    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
    zepam
    -0.46
    ghan
    -0.46
    stretchr
    -0.45
     ducha
    -0.45
    laceae
    -0.44
    Související
    -0.44
     Viitattu
    -0.44
    fjspx
    -0.44
    ינוך
    -0.43
    ruf
    -0.43
    POSITIVE LOGITS
     model
    4.49
    model
    4.07
     Model
    3.92
    Model
    3.67
     MODEL
    3.62
     models
    3.43
    MODEL
    3.25
     modelo
    3.23
     modèle
    3.19
     모델
    3.13
    Activations Density 0.395%

    No Known Activations