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. 10-GEMMASCOPE-RES-16K
    6. 2821
    Prev
    Next
    INDEX
    Explanations

    patterns and relationships in numerical data or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -0.73
    kháu
    -0.61
    GoogleApiClient
    -0.58
     مرئيه
    -0.58
     Diakses
    -0.55
    posedge
    -0.54
     Reſ
    -0.53
    VIAF
    -0.52
     tiegħek
    -0.52
     neuve
    -0.52
    POSITIVE LOGITS
    LabelTagHelper
    0.86
    PRNewswire
    0.66
     BoxDecoration
    0.66
    migrationBuilder
    0.65
    ParallelGroup
    0.64
    tagext
    0.58
    RenderAtEndOf
    0.58
    WriteTagHelper
    0.57
    TextWatcher
    0.54
    BorderFactory
    0.53
    Activations Density 1.974%

    No Known Activations