Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 16365
    Prev
    Next
    INDEX
    Explanations

    CSS styling properties and values

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

    CSS color values (rgb, rgba, hex)

    np_acts-logits-general · gemini-2.0-flash

    border-style css properties

    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
    MemoryWarning
    -1.00
     ujednoznacz
    -0.59
    PerformLayout
    -0.53
     المعيارى
    -0.53
     viewDidLoad
    -0.52
    pyplot
    -0.52
     khas
    -0.50
    WriteBarrier
    -0.48
    ApiOperation
    -0.48
    scalatest
    -0.47
    POSITIVE LOGITS
    MENAFN
    0.68
     inherit
    0.65
     ${({
    0.61
     transparent
    0.61
     none
    0.59
     unset
    0.59
    tvguidetime
    0.58
     rgba
    0.57
     url
    0.57
     calc
    0.56
    Activations Density 0.187%

    No Known Activations