© 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. 3538
    Prev
    Next
    INDEX
    Explanations

    words related to the visibility and security of devices integrated into vehicles

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

    Indicates something is "too" [adjective]

    np_acts-logits-general · gemini-2.0-flash

    too too baggy, heavy, cumbersome

    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
    TestTools
    -0.71
    AutoScale
    -0.66
     تضيفلها
    -0.60
     بيها
    -0.57
     الحره
    -0.55
     econó
    -0.53
     saites
    -0.52
    doctype
    -0.51
    windowFixed
    -0.49
     boils
    -0.49
    POSITIVE LOGITS
     unsightly
    1.01
     inconvenient
    1.00
     inconvenience
    0.94
     awkward
    0.94
     annoying
    0.86
     uncomfortable
    0.83
     unwelcome
    0.82
     distracting
    0.82
     conspicuous
    0.82
     cumbersome
    0.81
    Activations Density 0.296%

    No Known Activations