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. 7-GEMMASCOPE-RES-16K
    6. 6310
    Prev
    Next
    INDEX
    Explanations

    instances of the "sha" integrity attribute and references to various programming packages and libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yield
    -0.56
    WEBPACK
    -0.56
    اجة
    -0.55
    客房
    -0.55
     rebaj
    -0.54
     defaultstate
    -0.54
    antd
    -0.54
    出版年
    -0.54
    Yours
    -0.53
     Rechnung
    -0.52
    POSITIVE LOGITS
    AddTagHelper
    1.29
    AddHtmlAttribute
    1.05
    AnchorStyles
    0.99
    viewDidLoad
    0.96
    DockStyle
    0.94
    swift
    0.85
    ']").
    0.82
    AxisAlignment
    0.78
    aarrggbb
    0.78
    RectangleBorder
    0.77
    Activations Density 0.011%

    No Known Activations