© 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. 1893
    Prev
    Next
    INDEX
    Explanations

    references to journals and the act of journaling

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

    journaling or diaries

    np_acts-logits-general · gemini-2.0-flash

    personal writing and documentation

    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
    +:+
    -0.89
    +#+#
    -0.82
    ConstraintMaker
    -0.71
    webElementGuid
    -0.69
    IsContent
    -0.69
     ComVisible
    -0.69
    Datuak
    -0.67
    yntaxException
    -0.66
     costumi
    -0.66
    IntoConstraints
    -0.65
    POSITIVE LOGITS
     journal
    1.23
     diary
    1.17
     notebook
    1.07
     journals
    1.05
     Journal
    1.05
    journal
    1.02
    Journal
    1.02
     journaling
    1.02
     notebooks
    1.00
     Diary
    0.94
    Activations Density 0.146%

    No Known Activations