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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4841
    Prev
    Next
    INDEX
    Explanations

    technical terms related to liquid crystals and their optical properties

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

    preceding "Group" and other capitalized words

    np_acts-logits-general · gemini-2.0-flash

    resource group or tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     referrerpolicy
    -0.58
    AutoField
    -0.57
    +#+#
    -0.55
    󠁢
    -0.55
    帖最后由
    -0.51
    таратура
    -0.50
    tonode
    -0.47
     فريبيس
    -0.47
    AndEndTag
    -0.47
    ViewImports
    -0.46
    POSITIVE LOGITS
     RTC
    0.42
     IFA
    0.42
     Heap
    0.41
     Puck
    0.41
     purs
    0.40
     Durga
    0.40
     DT
    0.39
     Rug
    0.39
     RCA
    0.39
     GES
    0.39
    Activations Density 0.980%

    No Known Activations