© 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. 31-GEMMASCOPE-RES-16K
    11. 13662
    Prev
    Next
    INDEX
    Explanations

    themes of confinement and a desire for freedom

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

    words or phrases describing people being physically confined, trapped, or restricted in movement or space.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.44
    tangentMode
    -0.42
    Diret
    -0.40
    TagNumber
    -0.36
    PRIME
    -0.35
     pulito
    -0.35
     sumpay
    -0.35
    richting
    -0.34
     Substanz
    -0.34
     vastaan
    -0.34
    POSITIVE LOGITS
     trapped
    1.77
     stuck
    1.62
     locked
    1.45
    Stuck
    1.45
    stuck
    1.41
     Stuck
    1.37
     confined
    1.31
     imprisoned
    1.23
     confinement
    1.22
    locked
    1.20
    Activations Density 0.540%

    No Known Activations