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. 1-GEMMASCOPE-RES-16K
    6. 7190
    Prev
    Next
    INDEX
    Explanations

    references to specific technical parameters or terms related to experimental methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.92
    ChildScrollView
    -0.90
    DockStyle
    -0.90
     AspNetCore
    -0.89
    SharedDtor
    -0.87
     ―――――
    -0.84
     للاسماء
    -0.84
     مرئيه
    -0.81
    AccessorTable
    -0.77
    KommentareTeilen
    -0.76
    POSITIVE LOGITS
     Sar
    1.24
     TR
    1.23
     Tr
    1.16
    Sar
    1.07
     sar
    0.99
    sar
    0.96
     Tri
    0.95
    Tr
    0.91
     Tre
    0.85
     Ta
    0.83
    Activations Density 0.060%

    No Known Activations