© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5747
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to physical strain or injury

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

    Being stuck or trapped

    np_acts-logits-general · gemini-2.0-flash

    stuck, trapped, or contained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.60
     bezeichneter
    -0.60
     Abweich
    -0.58
     acquittal
    -0.54
     zacht
    -0.54
     remission
    -0.53
    PreferredItem
    -0.53
     requestCode
    -0.53
     offsets
    -0.53
     ruffle
    -0.52
    POSITIVE LOGITS
     locked
    1.71
     stuck
    1.64
     trapped
    1.58
     Stuck
    1.46
    locked
    1.46
    stuck
    1.46
     Locked
    1.43
    Stuck
    1.39
    Locked
    1.28
     tight
    1.28
    Activations Density 0.626%

    No Known Activations