© 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. 20-GEMMASCOPE-RES-16K
    11. 11133
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and advice

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

    Follows "correct" and precedes a personal pronoun

    np_acts-logits-general · gemini-2.0-flash

    correct me if i'm wrong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.62
    AnimationsModule
    -0.59
     }}"></
    -0.58
    いきましょう
    -0.57
    Ils
    -0.55
    きましょう
    -0.54
    weakSelf
    -0.54
    みましょう
    -0.54
    ")->
    -0.53
    PhysRevLett
    -0.53
    POSITIVE LOGITS
     my
    3.11
     myself
    2.24
    my
    2.23
     meiner
    2.22
     I
    2.21
     mijn
    2.21
     meines
    2.19
     моих
    2.10
     моего
    2.06
     tôi
    2.04
    Activations Density 3.248%

    No Known Activations