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. 4796
    Prev
    Next
    INDEX
    Explanations

    occurrences of programming function calls and method invocations

    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
    IsContent
    -1.02
     يتيمه
    -0.93
     snippetHide
    -0.92
    RegistryLite
    -0.88
    Personendaten
    -0.87
    oredCriteria
    -0.86
     LoggerFactory
    -0.85
    sizeCache
    -0.82
    WriteBarrier
    -0.80
    يكب
    -0.78
    POSITIVE LOGITS
    postDelayed
    0.50
    HTTPResponse
    0.48
    OREM
    0.43
    AreEqual
    0.43
    مثل
    0.42
     civiles
    0.42
    PHEN
    0.41
     bile
    0.41
     mimo
    0.41
    OURCE
    0.41
    Activations Density 0.445%

    No Known Activations