© 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. 13339
    Prev
    Next
    INDEX
    Explanations

    terms related to illegal or unethical actions and their consequences

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

    ending in "ate", "ated", "ating", "ation"

    np_acts-logits-general · gemini-2.0-flash

    stems for -ate, -ation, -ator words

    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
    AndEndTag
    -0.92
    EndInit
    -0.65
     Италијани
    -0.65
    TemporalType
    -0.64
     }{@
    -0.63
     AppComponent
    -0.62
    addCriterion
    -0.61
    Personendaten
    -0.61
    MemoryWarning
    -0.59
    ItemBackground
    -0.56
    POSITIVE LOGITS
    ating
    1.63
    ated
    1.62
    ation
    1.50
    ations
    1.27
    ATED
    1.25
    ATING
    1.15
    ATION
    1.12
    ators
    1.12
    ator
    1.10
    ate
    0.92
    Activations Density 0.391%

    No Known Activations