© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12574
    Prev
    Next
    INDEX
    Explanations

    subjective evaluations and feedback on services, experiences, or products

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

    Positive feedback and appreciation

    np_acts-logits-general · gemini-2.0-flash

    positive sentiment and ease

    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
    )".
    -0.70
    webElementGuid
    -0.67
     usw
    -0.64
    ).\\
    -0.64
    )”.
    -0.64
     osv
    -0.63
    ).}
    -0.61
    ).
    
    -0.60
    ichè
    -0.59
    *),
    -0.59
    POSITIVE LOGITS
     hope
    0.82
    <eos>
    0.71
     .
    0.67
     its
    0.66
     ,
    0.66
     I
    0.65
     great
    0.64
     peccato
    0.62
     they
    0.62
    Great
    0.62
    Activations Density 0.161%

    No Known Activations