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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15702
    Prev
    Next
    INDEX
    Explanations

    code constructs related to data handling and manipulation

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

    Java/C# code snippets containing Lists

    np_acts-logits-general · gemini-2.0-flash

    Declaring lists and collections

    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
     AssemblyTitle
    -0.70
    MENAFN
    -0.69
    Sklici
    -0.60
    Sucesor
    -0.59
    Зноскі
    -0.57
    awtextra
    -0.57
    ngrx
    -0.55
    OrFail
    -0.53
     strpos
    -0.52
    avage
    -0.50
    POSITIVE LOGITS
    IUrlHelper
    0.79
    FlatList
    0.66
    Personensuche
    0.64
    の中から
    0.60
     dataSnapshot
    0.59
    Obrázky
    0.58
     chronological
    0.56
    =[]
    0.55
     []*
    0.54
     Lordships
    0.54
    Activations Density 0.150%

    No Known Activations