© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9860
    Prev
    Next
    INDEX
    Explanations

    information related to prominent figures and their accomplishments

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

    editors or journalism

    np_acts-logits-general · gemini-2.0-flash

    editor or editors

    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
     Dr
    -0.43
    Dr
    -0.42
    刻
    -0.42
     llave
    -0.40
    attu
    -0.39
     esegu
    -0.38
    ({});
    -0.37
    atser
    -0.37
     ВО
    -0.37
    bcrypt
    -0.37
    POSITIVE LOGITS
     editors
    1.61
     editorial
    1.58
     editor
    1.52
     journalistic
    1.52
     journalism
    1.50
     journalists
    1.39
     Journalism
    1.34
     Editorial
    1.33
     Editor
    1.30
     Journalists
    1.27
    Activations Density 0.449%

    No Known Activations