© 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. 3853
    Prev
    Next
    INDEX
    Explanations

    mentions of conspiracy and political manipulation

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

    "of" followed by "the"

    np_acts-logits-general · gemini-2.0-flash

    most of the

    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
    sidemargin
    -0.84
    SuppressMessage
    -0.76
    المكان
    -0.71
    Gizmos
    -0.67
    oneofs
    -0.65
     ligiloj
    -0.65
    RTLR
    -0.65
    DotNetBar
    -0.64
    脚注の使い方
    -0.64
     dwie
    -0.64
    POSITIVE LOGITS
     what
    0.73
     us
    0.57
     it
    0.56
    ValueStyle
    0.53
     these
    0.52
    enumii
    0.49
     this
    0.49
    Ditto
    0.47
     them
    0.47
    unknownFields
    0.47
    Activations Density 0.128%

    No Known Activations