© 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. 1315
    Prev
    Next
    INDEX
    Explanations

    instances of the word "erred."

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

    Follows a noun or adjective

    np_acts-logits-general · gemini-2.0-flash

    following titles and introductions

    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
    AndEndTag
    -0.55
    SequentialGroup
    -0.51
     closest
    -0.51
    OGND
    -0.51
    ValueGenerated
    -0.50
    endphp
    -0.49
    UpInside
    -0.48
    rafa
    -0.48
    ohist
    -0.48
     noDo
    -0.47
    POSITIVE LOGITS
    ArgsConstructor
    0.74
     enough
    0.70
     myſelf
    0.69
    enough
    0.62
     HasFactory
    0.60
    Baik
    0.60
     Numerade
    0.60
     lắm
    0.60
    CodeAttribute
    0.59
     ſeveral
    0.58
    Activations Density 0.044%

    No Known Activations