© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 10430
    Prev
    Next
    INDEX
    Explanations

    situations related to being trapped or stuck

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngrx
    -0.48
    ผ่าน
    -0.45
    招呼
    -0.44
     tamp
    -0.44
    तिहास
    -0.42
     Saunders
    -0.42
     readiness
    -0.41
     Brutus
    -0.41
    signee
    -0.41
    DebuggerNonUser
    -0.40
    POSITIVE LOGITS
     trapped
    0.99
     stuck
    0.95
    Stuck
    0.89
     Stuck
    0.89
    stuck
    0.81
    ########.
    0.74
     stranded
    0.73
     AssemblyCulture
    0.70
     predicament
    0.70
     EconPapers
    0.69
    Activations Density 0.367%

    No Known Activations