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. 2-GEMMASCOPE-RES-16K
    6. 14952
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to margins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.91
    ########.
    -0.83
     AssemblyCulture
    -0.80
    webElementXpaths
    -0.72
    PositiveButton
    -0.70
    Xna
    -0.69
    encodeWith
    -0.68
    assertNull
    -0.68
    ProcessEvent
    -0.67
    +#+
    -0.63
    POSITIVE LOGITS
     margin
    3.94
    margin
    3.49
     Margin
    3.46
    Margin
    3.15
     margins
    3.11
    MARGIN
    2.49
    margins
    2.37
     marginal
    2.08
    Margins
    2.06
     marge
    2.01
    Activations Density 0.055%

    No Known Activations