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. 12795
    Prev
    Next
    INDEX
    Explanations

    mentions of fellowship programs and organizational roles in technological or entrepreneurial contexts

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

    Followed by the word "program"

    np_acts-logits-general · gemini-2.0-flash

    programs and related words

    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
     unknownFields
    -0.57
    orianCalendar
    -0.54
    onAttach
    -0.52
    ibatis
    -0.50
    Šaltiniai
    -0.49
    easeOut
    -0.49
    xtick
    -0.46
    ]_
    -0.46
     AssemblyCulture
    -0.46
    ("")]
    -0.45
    POSITIVE LOGITS
     program
    4.48
    program
    4.06
     Program
    3.96
    Program
    3.89
     programme
    3.77
     PROGRAM
    3.67
     programs
    3.64
    PROGRAM
    3.50
     programa
    3.49
     Programs
    3.34
    Activations Density 0.365%

    No Known Activations