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. 20-GEMMASCOPE-RES-16K
    6. 1877
    Prev
    Next
    INDEX
    Explanations

    programming languages or coding syntax.

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

    PHP code snippets focusing on processing user input for specific operations and providing error handling or feedback on web forms.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    PHP opening tags and code blocks.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -1.04
    FunctionFlags
    -1.02
     فريبيس
    -0.97
    +#+#
    -0.96
    principalColumn
    -0.96
    CppMethod
    -0.94
    makeConstraints
    -0.84
    TestingModule
    -0.83
     كومونز
    -0.82
     otomatig
    -0.81
    POSITIVE LOGITS
     echo
    0.79
    php
    0.64
    ↵
    0.63
      
    0.62
     
    0.62
    ↵↵
    0.61
    0.59
                                   
    0.59
     if
    0.57
    <eos>
    0.55
    Activations Density 0.017%

    No Known Activations