Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3163
    Prev
    Next
    INDEX
    Explanations

    energy sources and related technologies

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

    before suffixes like "ism", "life", "basics"

    np_acts-logits-general · gemini-2.0-flash

    specific entities and groups

    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
     بيها
    -0.87
     linkovi
    -0.63
     escuchadas
    -0.63
    enumi
    -0.58
    therapist
    -0.58
     vœux
    -0.58
    berfläche
    -0.57
    стях
    -0.56
     peines
    -0.56
    roscope
    -0.56
    POSITIVE LOGITS
    NameInMap
    0.70
    _();
    0.63
     ownership
    0.62
    .")
    
    0.62
     Paglinawan
    0.61
     snippetHide
    0.61
     companies
    0.60
    lessness
    0.59
     communities
    0.59
     systems
    0.58
    Activations Density 1.268%

    No Known Activations