© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7801
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mechanical assemblies and their characteristics

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

    preceding nouns, often technical

    np_acts-logits-general · gemini-2.0-flash

    itself, stessa, نفسها

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    Vidite
    -0.86
    GEBURTSDATUM
    -0.82
    TagMode
    -0.77
    rungsseite
    -0.68
    IsPostBack
    -0.68
     Roskov
    -0.67
     >=",
    -0.67
    LookAnd
    -0.66
    зулта
    -0.65
    POSITIVE LOGITS
     stesso
    0.61
    といっても
    0.60
     itself
    0.60
    と言っても
    0.60
     stessa
    0.58
     نفسها
    0.56
     proprement
    0.56
     huo
    0.55
     dimaksud
    0.55
     themſelves
    0.53
    Activations Density 1.868%

    No Known Activations