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. 2531
    Prev
    Next
    INDEX
    Explanations

    code-related phrases and structures in programming, especially focusing on object-oriented concepts and method calls

    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
    IndentedString
    -0.99
    PreferredItem
    -0.85
    ArrowToggle
    -0.81
     متعلقه
    -0.75
     kasarigan
    -0.67
    parsedMessage
    -0.67
    Tē
    -0.56
     QtGui
    -0.56
    IonicModule
    -0.55
    WebElementEntity
    -0.55
    POSITIVE LOGITS
    MockBean
    0.69
    GenerationType
    0.68
    Cryptography
    0.62
    setopt
    0.61
    mybatisplus
    0.59
    SqlSession
    0.59
    JdbcTemplate
    0.53
    bibitem
    0.51
    SerializedName
    0.51
    Autowired
    0.50
    Activations Density 0.052%

    No Known Activations