© 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. 18-GEMMASCOPE-RES-16K
    11. 865
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to engineering and machinery failures

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

    Mechanical failure or breakage

    np_acts-logits-general · gemini-2.0-flash

    broke, failed, collapsed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.57
    NavigationView
    -0.56
    HtmlAttribute
    -0.53
     prolongation
    -0.52
     pleaf
    -0.50
    OptionsMenu
    -0.50
    enderror
    -0.50
     Réponses
    -0.50
     sessile
    -0.49
    ynb
    -0.49
    POSITIVE LOGITS
     failure
    1.21
     collapse
    1.21
     broke
    1.09
     breakdown
    1.06
     broken
    1.05
     collapsed
    1.05
    failure
    1.01
     break
    1.00
     Failure
    1.00
     Collapse
    0.99
    Activations Density 0.349%

    No Known Activations