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. 16-GEMMASCOPE-RES-16K
    6. 6403
    Prev
    Next
    INDEX
    Explanations

    phrases related to television and media censorship

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

    Punctuation after a word

    np_acts-logits-general · gemini-2.0-flash

    perform or conclude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -1.01
    DockStyle
    -0.98
    rungsseite
    -0.96
     disambiguazione
    -0.94
     autorytatywna
    -0.92
    principalColumn
    -0.92
    期刊论文
    -0.90
    CloseOperation
    -0.88
    twimg
    -0.87
    NameInMap
    -0.86
    POSITIVE LOGITS
     péld
    0.47
    APES
    0.47
     my
    0.44
     pienso
    0.44
     id
    0.43
    違い
    0.43
     lenne
    0.41
    を通して
    0.41
     iria
    0.40
    ling
    0.40
    Activations Density 0.247%

    No Known Activations