© 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. 18-GEMMASCOPE-RES-16K
    11. 11767
    Prev
    Next
    INDEX
    Explanations

    references to names or entities related to people and their actions

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

    starting with "Tak", "Mak", or "Liv"

    np_acts-logits-general · gemini-2.0-flash

    tak or mak variants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    es
    -0.96
    ه
    -0.82
     pylint
    -0.79
    ollectionView
    -0.72
    e
    -0.69
    jsonwebtoken
    -0.69
     referenties
    -0.68
    esl
    -0.67
    enance
    -0.65
    eer
    -0.64
    POSITIVE LOGITS
    ings
    0.66
    __':
    0.50
    INGS
    0.48
    악
    0.48
    __":
    0.47
    paravant
    0.46
    PostBack
    0.46
     Mak
    0.46
    shar
    0.45
     protoimpl
    0.45
    Activations Density 0.336%

    No Known Activations