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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 1723
    Prev
    Next
    INDEX
    Explanations

    terms related to purchasing and acquisition

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

    starting with "Pur"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Pur

    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
    WithIOException
    -0.90
    HasAnnotation
    -0.82
     nahilalakip
    -0.73
     HasFactory
    -0.69
    bewerken
    -0.67
    oredCriteria
    -0.67
    }$​
    -0.66
    afficheront
    -0.66
    httphttps
    -0.65
     GenerationType
    -0.65
    POSITIVE LOGITS
     PUR
    1.03
     Pur
    0.94
    Pur
    0.89
    pur
    0.84
    PUR
    0.78
     pur
    0.74
     Purdy
    0.71
     purs
    0.62
    Попис
    0.60
     Purcell
    0.58
    Activations Density 0.078%

    No Known Activations