© 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. 3281
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional states and reactions

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

    textual errors or apologies for them

    np_acts-logits-general · gemini-2.0-flash

    emotional punctuation

    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
    ".
    -0.82
    )";
    -0.76
    aarrggbb
    -0.76
     NSCoder
    -0.75
    "})
    -0.74
    </caption>
    -0.74
    TagHelpers
    -0.74
    Personendaten
    -0.74
    uxxxx
    -0.74
     Ause
    -0.73
    POSITIVE LOGITS
     D
    0.93
     >
    0.83
     T
    0.83
     o
    0.79
     :(
    0.78
     O
    0.73
     ><
    0.71
     :/
    0.69
     sobs
    0.69
     ;-;
    0.68
    Activations Density 0.202%

    No Known Activations