© 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. 633
    Prev
    Next
    INDEX
    Explanations

    markers indicating the start of a new section or a significant transition in the text

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

    Code, questions, or technical documentation

    np_acts-logits-general · gemini-2.0-flash

    "Manager" followed by "and", "See"

    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
    ()];
    -0.62
    ())));
    -0.60
    ()-
    -0.55
    ErrUnexpectedEOF
    -0.53
    ()));
    -0.52
    маш
    -0.52
    ()<
    -0.49
    ()<<
    -0.49
    ритори
    -0.49
    ()));
    -0.48
    POSITIVE LOGITS
     itſelf
    0.83
    /**
    0.75
     Majefty
    0.75
     Houſe
    0.74
     myſelf
    0.74
     themſelves
    0.73
     himſelf
    0.71
     Reſ
    0.67
    ſelves
    0.65
     poffible
    0.64
    Activations Density 0.063%

    No Known Activations