© 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 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. 4802
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences or accounts expressed in the first person

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

    "I" followed by a past tense verb

    np_acts-logits-general · gemini-2.0-flash

    if i verb

    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
     probably
    -0.68
     Probably
    -0.65
    probably
    -0.64
    Probably
    -0.61
    니까
    -0.58
     provavelmente
    -0.57
     probabilmente
    -0.54
    aurait
    -0.53
     presumably
    -0.51
    enumi
    -0.50
    POSITIVE LOGITS
     were
    1.80
    Were
    1.65
     Were
    1.59
    were
    1.51
     WERE
    1.50
     weren
    1.49
    weren
    1.20
     hadn
    1.20
     ever
    1.15
     EVER
    0.88
    Activations Density 0.203%

    No Known Activations