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. 15695
    Prev
    Next
    INDEX
    Explanations

    phrases related to therapeutic developments and their implications in healthcare

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

    suggesting possibility or potential

    np_acts-logits-general · gemini-2.0-flash

    positive potential and possibilities

    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
    IndentedString
    -0.83
    帖最后由
    -0.75
    Personensuche
    -0.70
    еремо
    -0.69
    required
    -0.67
    Pratique
    -0.67
    AndEndTag
    -0.66
    enderror
    -0.65
    makeConstraints
    -0.65
     Required
    -0.65
    POSITIVE LOGITS
     potential
    1.34
     potentially
    1.33
    Potential
    1.25
     Potential
    1.22
    potential
    1.17
    potentially
    1.14
     possibilities
    1.14
     possibility
    1.13
     POTENTIAL
    1.08
     possible
    1.06
    Activations Density 0.615%

    No Known Activations