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. 24-GEMMASCOPE-RES-16K
    6. 8256
    Prev
    Next
    INDEX
    Explanations

    specific technical specifications related to multimedia features in devices

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

    Technical specifications/features of devices

    np_acts-logits-general · gemini-2.0-flash

    after Mirror Screen

    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
    tagHelperRunner
    -0.57
    RegressionTest
    -0.57
    ciler
    -0.56
    цездатний
    -0.48
     equipe
    -0.46
    Rhestr
    -0.46
    ặn
    -0.46
     Вікіпе
    -0.46
    HttpFoundation
    -0.46
    RectangleBorder
    -0.45
    POSITIVE LOGITS
     True
    0.68
     GenerationType
    0.63
    True
    0.62
    []){
    0.61
     improved
    0.61
    PageFactory
    0.57
     autorytatywna
    0.55
    AddTagHelper
    0.55
     FetchType
    0.54
    providedIn
    0.54
    Activations Density 0.213%

    No Known Activations