© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4331
    Prev
    Next
    INDEX
    Explanations

    instances of console logging and alerting in the code

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

    Code containing "log" or "amp"

    np_acts-logits-general · gemini-2.0-flash

    javascript console logging

    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
    MigrationBuilder
    -0.88
    parsedMessage
    -0.85
    <?,
    -0.80
    ^(@
    -0.78
    ✨:
    -0.78
    transQ
    -0.77
    ContentAsync
    -0.77
     صوتيه
    -0.77
     $_"
    -0.77
    Datuak
    -0.77
    POSITIVE LOGITS
    Slf
    0.59
     "
    0.56
    1
    0.51
    (
    0.49
    d
    0.49
    al
    0.48
    z
    0.48
    re
    0.47
     =
    0.47
    log
    0.46
    Activations Density 0.017%

    No Known Activations