© 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. 2854
    Prev
    Next
    INDEX
    Explanations

    references to personal growth and self-discovery

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

    Followed by a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    i and me

    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
    ")->
    -0.68
    いきましょう
    -0.63
    ſelves
    -0.63
    raszamy
    -0.63
    помним
    -0.63
    きましょう
    -0.61
    ſelf
    -0.60
    ">:
    -0.60
    CloseOperation
    -0.57
    みましょう
    -0.56
    POSITIVE LOGITS
     my
    3.65
     myself
    2.70
    my
    2.58
     mijn
    2.55
     meiner
    2.42
     meines
    2.41
     моих
    2.36
     моего
    2.33
    我的
    2.32
     meus
    2.29
    Activations Density 4.114%

    No Known Activations