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. 16-GEMMASCOPE-RES-16K
    6. 15819
    Prev
    Next
    INDEX
    Explanations

    terms related to software vulnerabilities, specifically those associated with buffer overflow issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or comments

    np_acts-logits-general · gemini-2.0-flash

    code safety and fixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    localctx
    -0.46
     pa
    -0.42
     auto
    -0.40
     nowo
    -0.39
     re
    -0.38
    auto
    -0.38
     authorised
    -0.38
     comprehensively
    -0.37
     conten
    -0.37
    rost
    -0.37
    POSITIVE LOGITS
     CWE
    1.49
    CWE
    1.01
     AssemblyTitle
    0.78
     doInBackground
    0.76
     Савезне
    0.75
     Majefty
    0.72
     يتيمه
    0.72
    InputBorder
    0.72
    ⓧ
    0.71
    RenderAtEndOf
    0.71
    Activations Density 0.036%

    No Known Activations