© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1408
    Prev
    Next
    INDEX
    Explanations

    references to community involvement and individual experiences

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

    Follows personal pronouns ("I", "we", "she")

    np_acts-logits-general · gemini-2.0-flash

    to help people accomplish things

    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
    Giving
    -0.50
     kijken
    -0.49
     ervan
    -0.49
    を抜
    -0.47
    SizedBox
    -0.46
     Misalnya
    -0.46
    Making
    -0.46
    delar
    -0.45
     Giving
    -0.44
     correctes
    -0.44
    POSITIVE LOGITS
     sorely
    0.69
     dearly
    0.69
     desperately
    0.65
    íncia
    0.64
    UTELY
    0.63
    hopefully
    0.61
     hopefully
    0.61
    typeorm
    0.59
     thankfully
    0.58
     cherish
    0.56
    Activations Density 0.289%

    No Known Activations