© 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. 10758
    Prev
    Next
    INDEX
    Explanations

    quotes and direct speech within a narrative context

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

    Quoted speech after a statement

    np_acts-logits-general · gemini-2.0-flash

    dialogue openers like "

    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
    あるいは
    -0.55
     portanto
    -0.53
     tačiau
    -0.51
     ),
    -0.50
    |}{\
    -0.48
     extraordinarily
    -0.48
     replete
    -0.47
     jenen
    -0.45
     (!)
    -0.45
    :=
    -0.45
    POSITIVE LOGITS
     initComponents
    0.98
     AssemblyVersion
    0.93
    contentLoaded
    0.88
     AssemblyCompany
    0.86
    principalColumn
    0.85
    .*")]
    0.85
    featureID
    0.82
    MemoryWarning
    0.81
    definitely
    0.81
     definitely
    0.81
    Activations Density 0.187%

    No Known Activations