© 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. 9823
    Prev
    Next
    INDEX
    Explanations

    specific punctuation marks and structure in the text, indicating the presence of quoted or referenced speech

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

    Text within quotation marks

    np_acts-logits-general · gemini-2.0-flash

    quoted ellipses and parentheticals

    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
    parsedMessage
    -0.97
     المعيارى
    -0.96
     فريبيس
    -0.95
    Portale
    -0.94
     nahilalakip
    -0.93
    évaluateur
    -0.89
    AsUp
    -0.88
     ويكيميديا
    -0.88
     GIPHY
    -0.85
    SharedDtor
    -0.85
    POSITIVE LOGITS
    …
    1.32
    ...
    1.31
     ...
    1.27
     …
    1.22
    ....
    0.99
    ….
    0.97
     […]
    0.91
     [...]
    0.89
    ..
    0.88
     “…
    0.85
    Activations Density 0.247%

    No Known Activations