© 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. 33-GEMMASCOPE-RES-16K
    6. 8628
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and concepts related to circuit design and signal processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     volume
    -0.43
     FU
    -0.39
    ]")]
    -0.39
     Volume
    -0.38
     smar
    -0.37
     textStatus
    -0.36
     constituents
    -0.36
    ctron
    -0.36
     lag
    -0.35
     pel
    -0.35
    POSITIVE LOGITS
     espelho
    0.58
     löyty
    0.53
     silencioso
    0.52
     ExecuteAsync
    0.50
     mijne
    0.50
     enfans
    0.48
     bibir
    0.47
     zijne
    0.47
     sanitarias
    0.46
     urusan
    0.46
    Activations Density 1.092%

    No Known Activations