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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 1463
    Prev
    Next
    INDEX
    Explanations

    instances of method calls and end-of-block indicators in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.83
    Бахар
    -0.77
    PasswordEncoder
    -0.76
    SourceChecksum
    -0.75
    ﹍﹍﹍
    -0.73
    DrawerToggle
    -0.73
     StatelessWidget
    -0.72
    Parcelize
    -0.72
    adaptiveStyles
    -0.70
    AlterField
    -0.70
    POSITIVE LOGITS
    BeginContext
    1.42
    Portail
    1.40
    بوابة
    1.27
    日閲覧
    0.92
     viewDidLoad
    0.85
    RegressionTest
    0.81
    原始内容存档于
    0.72
    Portale
    0.67
     jLabel
    0.61
    CharSequence
    0.58
    Activations Density 0.009%

    No Known Activations