© 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. 9570
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols indicating uncertainty or transitions in discussion

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

    Followed by a comma and a personal closing

    np_acts-logits-general · gemini-2.0-flash

    closing remarks

    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
    TagMode
    -0.72
     تانيه
    -0.69
    [])
    
    -0.61
     Moslem
    -0.61
    )))));
    -0.60
    اعمال
    -0.59
    ::::::::
    -0.59
    )*/
    -0.59
    +#+
    -0.57
    "))
    
    -0.57
    POSITIVE LOGITS
    EDIT
    1.38
    Edit
    1.34
     EDIT
    1.33
     edit
    1.33
    edit
    1.30
     Edit
    1.24
     edited
    1.03
    BTW
    1.02
    Regards
    0.96
    Cheers
    0.94
    Activations Density 0.296%

    No Known Activations