© 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. 18-GEMMASCOPE-RES-16K
    11. 6178
    Prev
    Next
    INDEX
    Explanations

    discussions of necessity and the influence of external forces on individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Forced" or "had to" situations

    np_acts-logits-general · gemini-2.0-flash

    forced action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.74
    SBATCH
    -0.64
    BeginContext
    -0.55
    ništ
    -0.55
     nonatomic
    -0.52
    LEEP
    -0.50
     selve
    -0.50
    そうそう
    -0.50
    yelitis
    -0.49
    นวน
    -0.49
    POSITIVE LOGITS
     terpaksa
    1.32
     resorted
    1.25
    只好
    1.21
     resorting
    1.15
     desperation
    1.09
     приходится
    1.06
     forced
    1.02
     выну
    1.02
    被迫
    0.99
    只能
    0.98
    Activations Density 0.382%

    No Known Activations