© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 7237
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

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

    Top-level domains (e.g., org, com, gov) after a period

    np_acts-logits-general · gemini-2.0-flash

    .org.com.gov.netrouter.jsproject.lock.jsonReview.prototype.save()

    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
    ContentAsync
    -0.92
     lenker
    -0.88
    extAlignment
    -0.87
     kasarigan
    -0.86
    ViewImports
    -0.83
    yntaxException
    -0.83
     חיצוניים
    -0.83
    Personensuche
    -0.81
     initComponents
    -0.81
     contextLoads
    -0.81
    POSITIVE LOGITS
    com
    0.80
    org
    0.73
    ».
    0.69
    }.
    0.65
    gov
    0.64
    <eos>
    0.64
    net
    0.64
    }$.
    0.63
    ()).
    0.63
    +.
    0.59
    Activations Density 0.452%

    No Known Activations