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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 4607
    Prev
    Next
    INDEX
    Explanations

    terms related to code vulnerabilities or weaknesses in programming practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.65
    Spoljašnje
    -0.65
    AsUp
    -0.64
    tagHelper
    -0.63
    subpackage
    -0.58
    Itoa
    -0.56
     photolibrary
    -0.55
    itisation
    -0.55
    umenical
    -0.55
    }{*}{
    -0.55
    POSITIVE LOGITS
    ExecutionContext
    4.30
     Execution
    0.80
    はじめに
    0.72
    ViewFeatures
    0.71
     للاسماء
    0.71
     متعلقه
    0.68
     execution
    0.67
    Context
    0.67
    execution
    0.63
    مراجع
    0.62
    Activations Density 0.006%

    No Known Activations