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. 15882
    Prev
    Next
    INDEX
    Explanations

    phrases related to design and user-oriented implementation

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

    "designed" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    designed for a purpose

    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
    用到
    -0.48
    ymce
    -0.48
    amos
    -0.48
    aarrggbb
    -0.47
     szükség
    -0.47
     avanti
    -0.46
     verwendeten
    -0.45
     عند
    -0.44
    XmlIgnore
    -0.43
    ದ
    -0.43
    POSITIVE LOGITS
     designed
    0.79
     pinulongan
    0.74
     bedoeld
    0.73
     specifically
    0.73
     purpose
    0.73
     suited
    0.72
     autorytatywna
    0.71
    designed
    0.70
     primarily
    0.69
     geared
    0.68
    Activations Density 0.182%

    No Known Activations