© 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. 3-GEMMASCOPE-RES-16K
    11. 6189
    Prev
    Next
    INDEX
    Explanations

    concepts related to power, control, and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gereken
    -0.45
     leggen
    -0.40
    щал
    -0.38
     Suiza
    -0.37
    Dado
    -0.36
     tomadas
    -0.36
     Cualquier
    -0.36
    ningss
    -0.35
    ]=>
    -0.34
     Selecciona
    -0.34
    POSITIVE LOGITS
    ImageContext
    0.66
     ***!
    0.65
    WriteTagHelper
    0.60
    NOPQRST
    0.60
     EconPapers
    0.58
    featureID
    0.58
     auprès
    0.57
    imageshack
    0.56
     nakalista
    0.56
    onAttach
    0.56
    Activations Density 0.288%

    No Known Activations