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. 5-GEMMASCOPE-RES-16K
    6. 8638
    Prev
    Next
    INDEX
    Explanations

    JavaScript export and import statements, specifically in the context of front-end frameworks and libraries

    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
    BackColor
    -0.79
    ('/:
    -0.76
    ("")]
    -0.66
    BeginInit
    -0.64
    UIControlState
    -0.61
    FormTagHelper
    -0.57
    TabIndex
    -0.56
    FXML
    -0.54
    ("/:
    -0.53
    BindView
    -0.52
    POSITIVE LOGITS
    xs
    1.52
     xs
    1.18
     XS
    0.97
    XS
    0.96
    colgroup
    0.92
    SourceChecksum
    0.89
    RegistryLite
    0.80
    HtmlAttribute
    0.80
     NOI
    0.79
     Superhosts
    0.78
    Activations Density 0.024%

    No Known Activations