© 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. 12601
    Prev
    Next
    INDEX
    Explanations

    details related to the design and functionality of connecting assemblies, particularly mechanical connections

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

    Fit, insert, attach, seal, or tighten something

    np_acts-logits-general · gemini-2.0-flash

    secure fit

    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
    mybatisplus
    -0.69
     ModelExpression
    -0.68
     متعلقه
    -0.64
     StatelessWidget
    -0.63
     Baus
    -0.61
    kmäler
    -0.60
     Chwiliwch
    -0.60
     handic
    -0.60
    MemoryWarning
    -0.59
     createState
    -0.57
    POSITIVE LOGITS
     tight
    0.92
     fit
    0.87
     snug
    0.86
     Tight
    0.84
     tighten
    0.82
    Tight
    0.81
    tight
    0.80
     secure
    0.80
     tightened
    0.78
     securely
    0.77
    Activations Density 0.510%

    No Known Activations