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. 18-GEMMASCOPE-RES-16K
    6. 8626
    Prev
    Next
    INDEX
    Explanations

    educational institutions and academic qualifications

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

    universities or colleges

    np_acts-logits-general · gemini-2.0-flash

    University after from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.78
    PreferredItem
    -0.77
    ContentAsync
    -0.76
     nakalista
    -0.74
     propOrder
    -0.74
    bootstrapcdn
    -0.73
    GEBURTSDATUM
    -0.73
    يميديا
    -0.73
     autorytatywna
    -0.72
    errHandler
    -0.70
    POSITIVE LOGITS
     University
    0.59
    University
    0.52
     UNIVERSITY
    0.46
     Univ
    0.46
     betweenstory
    0.43
     Verd
    0.42
    start
    0.40
     Université
    0.40
    Universidad
    0.39
    complexType
    0.39
    Activations Density 0.144%

    No Known Activations