© 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. 1356
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and numeric values in code or programming contexts

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

    Code or configuration snippets ending with a property access

    np_acts-logits-general · gemini-2.0-flash

    programming code snippets

    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
    tvguidetime
    -0.88
     NSCoder
    -0.70
     smtplib
    -0.70
     aéreo
    -0.61
     getPassword
    -0.61
    remadura
    -0.59
     zipfile
    -0.59
     actionMode
    -0.58
     pymysql
    -0.58
     pyplot
    -0.58
    POSITIVE LOGITS
     "..\..\..\
    0.70
     _('
    0.68
    hasOwnProperty
    0.63
    }{*}{
    0.61
    last
    0.61
    $("#
    0.59
    =$("#
    0.58
     _("
    0.57
    ')['
    0.56
    eeq
    0.56
    Activations Density 0.479%

    No Known Activations