© 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. 1149
    Prev
    Next
    INDEX
    Explanations

    sentences that introduce contrasting statements or circumstances

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

    Sentences starting with "Though"

    np_acts-logits-general · gemini-2.0-flash

    concessive clauses

    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
     للمعارف
    -0.71
     entanto
    -0.68
    WebControls
    -0.54
    Them
    -0.51
    وانید
    -0.50
    เลย
    -0.49
     način
    -0.48
     PDC
    -0.48
    them
    -0.48
     natomiast
    -0.48
    POSITIVE LOGITS
     there
    1.12
     they
    1.11
     not
    1.10
     it
    1.07
     admittedly
    1.04
     we
    1.00
     technically
    0.92
     sometimes
    0.84
     rarely
    0.83
     somewhat
    0.82
    Activations Density 0.070%

    No Known Activations