© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 15035
    Prev
    Next
    INDEX
    Explanations

    action verbs related to achieving results or outcomes

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

    Follows a verb, then "it" or "them"

    np_acts-logits-general · gemini-2.0-flash

    verbs followed by it or them

    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
    Its
    -0.97
     Its
    -0.87
    they
    -0.80
    awtextra
    -0.71
    fony
    -0.70
     they
    -0.70
    AnchorTagHelper
    -0.70
     ProtoMessage
    -0.70
     jsPsych
    -0.68
     إنها
    -0.67
    POSITIVE LOGITS
     them
    1.67
    them
    0.92
     him
    0.84
     THEM
    0.72
     tham
    0.64
     said
    0.62
    Them
    0.60
    hem
    0.57
     Them
    0.57
     eux
    0.57
    Activations Density 0.282%

    No Known Activations