© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12623
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of people and places

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

    following capitalized words

    np_acts-logits-general · gemini-2.0-flash

    starts of names followed by suffixes

    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
    SequentialGroup
    -0.59
     prestations
    -0.54
     dimensiones
    -0.51
     conséquences
    -0.50
     correctement
    -0.48
     andra
    -0.47
     exemples
    -0.47
    ülü
    -0.46
     serius
    -0.46
     utama
    -0.46
    POSITIVE LOGITS
     doubtnut
    1.00
     vectorstock
    0.76
     pngtree
    0.74
     Athenians
    0.74
     ་་
    0.73
     Colón
    0.72
     isNameExpr
    0.71
     itſelf
    0.71
     Efq
    0.71
     Jefus
    0.71
    Activations Density 0.275%

    No Known Activations