© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9143
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to specific medical conditions and biochemical processes

    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
     CanadaChoose
    -0.47
     inver
    -0.43
    ❉
    -0.42
    fitrión
    -0.38
     Italijanski
    -0.37
     eletr
    -0.37
     inverter
    -0.36
     mö
    -0.36
     Inverse
    -0.35
     Auk
    -0.35
    POSITIVE LOGITS
    ial
    0.68
     ProtoMessage
    0.61
     Snake
    0.56
    snake
    0.56
    ica
    0.53
    querySelector
    0.52
     snake
    0.52
     sn
    0.51
     Bell
    0.51
     Sacrific
    0.51
    Activations Density 1.291%

    No Known Activations