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. 13034
    Prev
    Next
    INDEX
    Explanations

    references to concepts of engineering, technology, and systems

    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
     Majefty
    -0.87
     purpoſe
    -0.86
     Chriftian
    -0.76
     fevere
    -0.75
    쨌
    -0.73
     pleaſure
    -0.73
     myſelf
    -0.72
     ſtate
    -0.71
    subsubsection
    -0.71
     Monfieur
    -0.71
    POSITIVE LOGITS
    oa̍t
    0.72
    ண்டும்
    0.70
    ագրություններ
    0.67
    |)
    0.66
    ็จ
    0.63
    endphp
    0.62
    Cyfeiriadau
    0.61
    esModule
    0.59
    //
    0.59
    <>();
    0.58
    Activations Density 0.407%

    No Known Activations