© 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. 24-GEMMASCOPE-RES-16K
    11. 14622
    Prev
    Next
    INDEX
    Explanations

    terms related to appointments and positions of authority

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

    Following certain prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    taking over a new role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.57
     AssemblyCulture
    -0.56
     FormsModule
    -0.56
    setVerticalGroup
    -0.55
    trise
    -0.52
     saites
    -0.52
     lenker
    -0.51
    Ẻ
    -0.51
    __(/*!
    -0.50
     متعلقه
    -0.50
    POSITIVE LOGITS
     replacing
    1.94
     replace
    1.87
     replaces
    1.78
     replaced
    1.66
     Replacing
    1.62
     replacement
    1.61
    Replacing
    1.57
     assume
    1.55
    replacing
    1.53
     assumed
    1.49
    Activations Density 0.323%

    No Known Activations