© 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. 10-GEMMASCOPE-RES-16K
    11. 15858
    Prev
    Next
    INDEX
    Explanations

    terms related to breakdown or collapse in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jefus
    -0.49
     pinulongan
    -0.49
    Cyfarwyddwr
    -0.48
     Anſ
    -0.48
    moiselle
    -0.48
     juſ
    -0.47
     poffible
    -0.45
    UFO
    -0.45
    Personendaten
    -0.44
    bias
    -0.44
    POSITIVE LOGITS
     collapse
    1.23
     collapsed
    1.03
     collapses
    0.99
     Collapse
    0.95
     collapsing
    0.95
    collapse
    0.93
    崩壊
    0.83
     breakdown
    0.83
    Collapse
    0.81
     disintegration
    0.80
    Activations Density 0.546%

    No Known Activations