© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1491
    Prev
    Next
    INDEX
    Explanations

    statements or phrases expressing opinions or beliefs regarding significant issues

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

    Follows the word "that"

    np_acts-logits-general · gemini-2.0-flash

    referring to facts or previous statements

    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
    DockStyle
    -0.80
     ModelExpression
    -0.80
    tvguidetime
    -0.76
     @"/
    -0.71
    ContentAsync
    -0.69
    ImageContext
    -0.67
    Datuak
    -0.64
     createState
    -0.63
    SharedCtor
    -0.63
    Välislingid
    -0.62
    POSITIVE LOGITS
     idea
    0.79
     those
    0.79
     this
    0.78
     fact
    0.74
     aspect
    0.74
     concept
    0.71
     distinction
    0.71
     scenario
    0.68
     process
    0.68
     there
    0.68
    Activations Density 0.116%

    No Known Activations