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. 12-GEMMASCOPE-RES-16K
    6. 10227
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate company overviews or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    וי
    -0.53
    tic
    -0.46
    writerow
    -0.46
    edig
    -0.44
    y
    -0.44
    ال
    -0.43
     male
    -0.43
    доступ
    -0.43
    benhavn
    -0.42
    年度
    -0.42
    POSITIVE LOGITS
    :✨
    0.93
     صوتيه
    0.92
    ExtendWith
    0.86
     дописавши
    0.84
     ujednoznacz
    0.83
     AssemblyCompany
    0.82
    rungsseite
    0.80
    GEBURTSDATUM
    0.79
    مصادر
    0.78
     Италијани
    0.77
    Activations Density 0.097%

    No Known Activations