© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4306
    Prev
    Next
    INDEX
    Explanations

    references to meta-analysis in scientific or academic contexts

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

    "Meta" or "meta"

    np_acts-logits-general · gemini-2.0-flash

    meta-analysis, metagenomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ControllerBase
    -0.69
    orianCalendar
    -0.59
    matchCondition
    -0.58
    opengl
    -0.53
    YMS
    -0.49
    ʺ
    -0.49
     Brink
    -0.49
    OpenHelper
    -0.49
    __((
    -0.48
    IBinder
    -0.48
    POSITIVE LOGITS
     Meta
    1.27
     meta
    1.26
     META
    1.20
    meta
    1.18
    Meta
    1.14
     metas
    1.05
     MET
    0.97
    META
    0.88
     мета
    0.87
    metas
    0.86
    Activations Density 0.091%

    No Known Activations