© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5442
    Prev
    Next
    INDEX
    Explanations

    references to entities denoted by the letter "M" or variations thereof

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

    Follows the letter M

    np_acts-logits-general · gemini-2.0-flash

    Mumbling, mornings, MMT, Moche, MKE

    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
     fij
    -0.53
     interesar
    -0.52
    ent
    -0.51
    bootstrapcdn
    -0.50
    eno
    -0.48
    enu
    -0.48
    Reach
    -0.47
     spie
    -0.46
    ount
    -0.46
    TabStop
    -0.45
    POSITIVE LOGITS
     neceff
    0.76
     getM
    0.74
     Majefty
    0.69
     itſelf
    0.68
    hematical
    0.66
     NDEBUG
    0.66
     doubtnut
    0.65
     Monfieur
    0.65
     فريبيس
    0.65
    tached
    0.64
    Activations Density 0.320%

    No Known Activations