© 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. 22-GEMMASCOPE-RES-16K
    11. 2461
    Prev
    Next
    INDEX
    Explanations

    references to dual perspectives or contrasts in behavior or themes

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

    Following demonstrative pronouns

    np_acts-logits-general · gemini-2.0-flash

    articles followed by nouns

    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
     Надо
    -0.89
     biß
    -0.83
     daß
    -0.81
    Надо
    -0.79
     freilich
    -0.77
     variously
    -0.74
     eminently
    -0.73
     weitgehend
    -0.72
    Herzliche
    -0.72
     надо
    -0.71
    POSITIVE LOGITS
     downfall
    0.83
    casted
    0.79
     demnach
    0.76
     hierbei
    0.72
     ideologies
    0.70
     advancements
    0.70
     entirety
    0.69
     anteriormente
    0.69
     Furthermore
    0.67
    asantry
    0.67
    Activations Density 0.449%

    No Known Activations