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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 12847
    Prev
    Next
    INDEX
    Explanations

    contact information and communication details in a professional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -0.53
     the
    -0.52
    Tämä
    -0.51
     appunto
    -0.51
     Wikimedijinoj
    -0.51
     this
    -0.50
    новниш
    -0.50
    iego
    -0.48
    Хро
    -0.48
    botten
    -0.47
    POSITIVE LOGITS
     FAX
    0.67
     fax
    0.66
    UpInside
    0.65
     telephone
    0.65
     Phones
    0.65
     telephones
    0.65
     PHONE
    0.64
    phone
    0.64
     Phone
    0.61
     IndexPath
    0.60
    Activations Density 0.087%

    No Known Activations