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. 3020
    Prev
    Next
    INDEX
    Explanations

    references to purity or pure qualities in various contexts

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

    "pure" or its translations

    np_acts-logits-general · gemini-2.0-flash

    pure [collocation]

    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
    omitempty
    -0.81
     beginnetje
    -0.74
    __':
    -0.71
    transQ
    -0.71
     Monfieur
    -0.70
     indisponible
    -0.70
    estacks
    -0.69
     tää
    -0.67
    __':
    
    -0.66
    lapsingToolbar
    -0.65
    POSITIVE LOGITS
     pure
    1.31
     Pure
    1.24
    pure
    1.16
    Pure
    1.13
     PURE
    1.11
    bred
    0.98
    PURE
    0.94
     murni
    0.91
    纯
    0.83
     pura
    0.81
    Activations Density 0.071%

    No Known Activations