© 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. 2-GEMMASCOPE-RES-16K
    11. 9133
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and their references related to studies and data analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    iettivo
    -0.46
    ContentAsync
    -0.46
    labelControl
    -0.44
     Bentham
    -0.44
    riebene
    -0.43
    GTCX
    -0.43
    évaluateur
    -0.43
     TestBed
    -0.43
    cesz
    -0.43
     okuyayım
    -0.42
    POSITIVE LOGITS
     snippetHide
    0.60
    iz
    0.58
     Phil
    0.53
     polymer
    0.51
     Cop
    0.50
     phil
    0.50
    Recur
    0.47
    ')")
    0.47
    Phil
    0.47
     pale
    0.47
    Activations Density 0.543%

    No Known Activations