© 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. 1345
    Prev
    Next
    INDEX
    Explanations

    punctuation marks used for sentence demarcation

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

    Sentences ending with numbers

    np_acts-logits-general · gemini-2.0-flash

    years ago

    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
     su
    -0.53
     i
    -0.52
     I
    -0.50
     over
    -0.49
     Peter
    -0.48
     J
    -0.48
     the
    -0.47
     min
    -0.47
     ob
    -0.47
     it
    -0.46
    POSITIVE LOGITS
     myſelf
    1.21
     Theſe
    1.20
     CreateTagHelper
    1.17
     Majefty
    1.03
     itſelf
    1.03
     Jefus
    1.01
     Anſ
    0.98
    ſelves
    0.98
     Houſe
    0.97
     purpoſe
    0.96
    Activations Density 0.050%

    No Known Activations