© 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. 13734
    Prev
    Next
    INDEX
    Explanations

    geographical locations in France

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

    France, French, or Paris

    np_acts-logits-general · gemini-2.0-flash

    French places and nationality

    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
     ainfi
    -1.25
     auffi
    -1.16
     auroit
    -1.10
     Majefty
    -1.08
     nôtre
    -1.07
     Efq
    -1.05
     purpoſe
    -1.04
     houſe
    -1.04
     enfans
    -1.04
     feroit
    -1.04
    POSITIVE LOGITS
     French
    1.74
     France
    1.66
    French
    1.45
    France
    1.42
     Paris
    1.39
     french
    1.36
     FRENCH
    1.24
    法国
    1.19
     francesa
    1.18
    Paris
    1.17
    Activations Density 0.601%

    No Known Activations