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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24-GEMMASCOPE-RES-16K
    6. 2293
    Prev
    Next
    INDEX
    Explanations

    references to awards and recognitions within the context of career achievements

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

    Followed by university names

    np_acts-logits-general · gemini-2.0-flash

    universities and news organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utilising
    -0.66
     optimised
    -0.66
     customised
    -0.61
     optimise
    -0.60
     organisational
    -0.60
     specialises
    -0.60
    ंदीखरीदारी
    -0.60
     utilised
    -0.59
     customise
    -0.59
     utilise
    -0.59
    POSITIVE LOGITS
     außer
    0.54
    PreferredItem
    0.50
     poros
    0.50
     ModelExpression
    0.48
     Munk
    0.48
    Inflater
    0.47
     Sơ
    0.47
    就在
    0.45
     Histor
    0.45
    newswire
    0.45
    Activations Density 0.110%

    No Known Activations