© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5388
    Prev
    Next
    INDEX
    Explanations

    situations involving feeling trapped or constrained, particularly in social or physical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    テンツ
    -0.46
    ISupport
    -0.43
     sudad
    -0.42
     tearDown
    -0.42
    исленность
    -0.42
     tirantes
    -0.40
    isNotBlank
    -0.40
     décontract
    -0.39
     desmotivaciones
    -0.39
     NOISE
    -0.39
    POSITIVE LOGITS
     trapped
    2.25
     stuck
    2.17
    stuck
    1.80
     Stuck
    1.79
    Stuck
    1.77
     trapping
    1.49
     trap
    1.48
     locked
    1.48
     stranded
    1.40
     traps
    1.25
    Activations Density 0.627%

    No Known Activations