© 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. 22-GEMMASCOPE-RES-16K
    11. 3134
    Prev
    Next
    INDEX
    Explanations

    phrases relating to events, gatherings, and achievements

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

    Adjectives describing people's qualities or skills

    np_acts-logits-general · gemini-2.0-flash

    professionals or individuals

    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
     démocr
    -0.93
     vœux
    -0.86
     nuages
    -0.67
     genoux
    -0.66
     vectorielles
    -0.64
     preuves
    -0.64
     sanitaires
    -0.64
     rêves
    -0.63
     écrits
    -0.62
     médec
    -0.62
    POSITIVE LOGITS
     professionals
    1.51
     members
    1.45
     practitioners
    1.45
     designers
    1.43
     participants
    1.43
     players
    1.43
     engineers
    1.42
     scientists
    1.41
     photographers
    1.40
     individuals
    1.38
    Activations Density 3.516%

    No Known Activations