© 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. 5685
    Prev
    Next
    INDEX
    Explanations

    technical terms related to vehicle performance and mechanics

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

    Shaking, swaying, or instability

    np_acts-logits-general · gemini-2.0-flash

    shaking and vibrations

    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
     sphinx
    -0.47
     Extragalactic
    -0.47
    prnewswire
    -0.45
    avanje
    -0.44
    zeciw
    -0.44
    گانی
    -0.44
    arean
    -0.43
     Merah
    -0.42
     taglia
    -0.42
    etches
    -0.41
    POSITIVE LOGITS
     shaking
    1.75
     shake
    1.72
     shakes
    1.59
     Shake
    1.54
    shake
    1.53
     vibration
    1.49
     shaken
    1.49
     shook
    1.48
     vibrations
    1.45
    Shake
    1.42
    Activations Density 0.313%

    No Known Activations