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. 4-GEMMASCOPE-RES-16K
    6. 10447
    Prev
    Next
    INDEX
    Explanations

    HTML input fields and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     W
    -0.50
    IsRequired
    -0.49
    lah
    -0.48
     Barker
    -0.47
     force
    -0.47
     way
    -0.46
    varo
    -0.46
    rav
    -0.45
     contact
    -0.45
     salaries
    -0.45
    POSITIVE LOGITS
    TestingModule
    1.08
    AddTagHelper
    1.08
     الحره
    0.97
     propOrder
    0.89
    StoryboardSegue
    0.86
    存于互联网档案馆
    0.85
     AssemblyCulture
    0.79
     >=",
    0.79
    SequentialGroup
    0.78
     viewDidLoad
    0.76
    Activations Density 0.060%

    No Known Activations