© 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. 33-GEMMASCOPE-RES-16K
    11. 216
    Prev
    Next
    INDEX
    Explanations

    phrases indicating attachment or adherence between objects

    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
    postsleuth
    -0.48
    ValueGeneration
    -0.46
     Einfluß
    -0.44
    richTextPanel
    -0.43
     correlation
    -0.43
     resourceCulture
    -0.42
    Cordialement
    -0.41
     noDo
    -0.41
    pography
    -0.41
    mandala
    -0.41
    POSITIVE LOGITS
     firmly
    0.94
     securely
    0.79
     tightly
    0.77
     onto
    0.74
     together
    0.65
     attach
    0.65
     solidly
    0.63
     permanently
    0.62
     firme
    0.61
     rigidly
    0.61
    Activations Density 0.377%

    No Known Activations