© 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. 10369
    Prev
    Next
    INDEX
    Explanations

    punctuation and citation references in texts

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

    Punctuation at the end of sentences

    np_acts-logits-general · gemini-2.0-flash

    citations and bibliographical references

    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
    Geplaatst
    -1.00
     ویکی‌پدیا
    -0.92
     незавершена
    -0.82
     كومونز
    -0.79
    NameInMap
    -0.77
    IsMutable
    -0.77
    nodoc
    -0.76
    Datuak
    -0.75
    +#+
    -0.73
    </thead>
    -0.73
    POSITIVE LOGITS
    ↵
    0.53
    <eos>
    0.52
    ↵↵
    0.49
    ↵↵↵↵↵
    0.46
    ↵↵↵
    0.44
     contient
    0.44
     Fehler
    0.43
     noastre
    0.42
    採
    0.42
     meglio
    0.42
    Activations Density 0.055%

    No Known Activations