© 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. 2-GEMMASCOPE-RES-16K
    6. 8363
    Prev
    Next
    INDEX
    Explanations

    references to filters and associated tagging processes in data systems

    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
     œuvres
    -0.36
     villes
    -0.32
     cap
    -0.30
    apnews
    -0.30
     Lieben
    -0.29
    cap
    -0.26
     života
    -0.26
     domaines
    -0.25
    }]
    -0.25
     ocur
    -0.25
    POSITIVE LOGITS
     filters
    1.20
     badges
    1.14
     stickers
    1.13
     tags
    1.13
     buttons
    1.13
     licenses
    1.09
     switches
    1.06
     bandages
    1.05
     brushes
    1.05
     masks
    1.05
    Activations Density 0.517%

    No Known Activations