Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10996
    Prev
    Next
    INDEX
    Explanations

    references to threats to democracy and political interference

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

    before periods or conjunctions related to society

    np_acts-logits-general · gemini-2.0-flash

    ideas of society, democracy, and planet

    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
    RenderAtEndOf
    -0.65
    씩
    -0.60
     Occasionally
    -0.59
     JAXBElement
    -0.57
    ்த்த
    -0.57
    msgTypes
    -0.57
     occasionally
    -0.56
    Occasionally
    -0.56
    persky
    -0.55
    ]")]
    -0.53
    POSITIVE LOGITS
     forever
    0.71
     tomorrow
    0.66
    forever
    0.63
     today
    0.63
     FOREVER
    0.61
     TODAY
    0.60
    ankind
    0.59
     tasche
    0.59
     jakim
    0.58
     globally
    0.57
    Activations Density 0.439%

    No Known Activations