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. 1-GEMMASCOPE-RES-16K
    6. 9566
    Prev
    Next
    INDEX
    Explanations

    codes and structured data related to network or system requests

    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
    RegistryLite
    -0.71
     CreateTagHelper
    -0.71
     ویکی‌پدیا
    -0.71
     propOrder
    -0.70
    +#+
    -0.69
     resourceCulture
    -0.68
     Poni
    -0.66
     informée
    -0.65
    hasMoreElements
    -0.65
    InjectAttribute
    -0.65
    POSITIVE LOGITS
    はじめに
    0.67
    SBATCH
    0.45
     BoxDecoration
    0.44
    principalTable
    0.43
    newcommand
    0.41
     sitting
    0.40
    Portale
    0.40
     individ
    0.40
     computa
    0.39
     ader
    0.39
    Activations Density 0.356%

    No Known Activations