© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14262
    Prev
    Next
    INDEX
    Explanations

    CSS style properties related to layout and positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or programming-related terms

    np_acts-logits-general · gemini-2.0-flash

    css, html, javascript, natural language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.71
     AssemblyProduct
    -0.55
    cshtml
    -0.53
     []:
    -0.53
    CreateModel
    -0.52
     Sotto
    -0.52
    Obrázky
    -0.52
    +#+
    -0.51
    "?
    -0.50
    routeProvider
    -0.50
    POSITIVE LOGITS
     !
    1.01
    !
    0.77
     betweenstory
    0.75
    !
    0.69
     !!
    0.65
     !!!
    0.63
    %!
    0.63
    IndentedString
    0.63
     !)
    0.62
     !!!!
    0.59
    Activations Density 0.069%

    No Known Activations