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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 9838
    Prev
    Next
    INDEX
    Explanations

    instances of the word "back" and its variations, indicating a focus on themes of returning or revisiting

    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
    ValueStyle
    -0.91
    حوالہ
    -0.82
    BagLayout
    -0.80
    MigrationBuilder
    -0.79
    DeleteBehavior
    -0.77
     ویکی‌پدیا
    -0.76
    ContentAsync
    -0.76
    NewRow
    -0.72
     AssemblyCulture
    -0.72
    MemoryWarning
    -0.71
    POSITIVE LOGITS
     returning
    1.32
     returned
    1.30
     return
    1.22
     Returned
    1.19
     returns
    1.17
     Returning
    1.14
    Returning
    1.07
    returned
    1.07
    returning
    1.07
    Returned
    1.05
    Activations Density 0.115%

    No Known Activations