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. 12931
    Prev
    Next
    INDEX
    Explanations

    statements regarding participation and reputation in community discussions

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

    Questions and answers

    np_acts-logits-general · gemini-2.0-flash

    answers

    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
    stateParams
    -0.45
    propTypes
    -0.42
    PullParser
    -0.41
     blast
    -0.40
     Blast
    -0.39
     Vors
    -0.39
     unik
    -0.38
    راث
    -0.38
     Mon
    -0.37
    Гла
    -0.37
    POSITIVE LOGITS
     answers
    0.98
     answered
    0.97
     answer
    0.92
    expandindo
    0.88
     Answers
    0.87
     answering
    0.87
     ANSWER
    0.83
    answers
    0.81
    answered
    0.80
     ANSWERS
    0.79
    Activations Density 0.724%

    No Known Activations