© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1300
    Prev
    Next
    INDEX
    Explanations

    phrases related to trust and community boundaries

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

    Follows a word indicating a condition or exception

    np_acts-logits-general · gemini-2.0-flash

    unless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    følgelig
    -0.78
    MessageTagHelper
    -0.70
     تضيفلها
    -0.70
     Exactos
    -0.65
    <![
    -0.61
     $_"
    -0.59
     greateſt
    -0.59
    StructEnd
    -0.58
    ressee
    -0.58
     ſtill
    -0.57
    POSITIVE LOGITS
     unless
    1.52
    unless
    1.33
     anything
    1.26
    Unless
    1.17
    anything
    1.16
     any
    1.16
     Unless
    1.13
     Anything
    1.12
     apapun
    1.10
     ANYTHING
    1.10
    Activations Density 0.541%

    No Known Activations