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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 7376
    Prev
    Next
    INDEX
    Explanations

    references to Microsoft, Spring Framework, and annotations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     internetowa
    -0.65
    Cyfeiriadau
    -0.62
     unknownFields
    -0.57
     Commencez
    -0.53
     Wikimedijinoj
    -0.52
     gynnwys
    -0.52
     idea
    -0.52
     Bode
    -0.52
     userService
    -0.51
    sidemargin
    -0.51
    POSITIVE LOGITS
     TextAppearance
    0.97
     оригіналу
    0.86
    aarrggbb
    0.82
    apimachinery
    0.79
    SpringBootTest
    0.77
     Microsoft
    0.77
    #
    0.76
     صوتيه
    0.70
     MessageBoxIcon
    0.70
    RenderAtEndOf
    0.69
    Activations Density 0.010%

    No Known Activations