© 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. 9721
    Prev
    Next
    INDEX
    Explanations

    references to cracking or breaks, often in a metaphorical or literal context

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

    relating to "crack" or "cracking"

    np_acts-logits-general · gemini-2.0-flash

    crack and variations

    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
    WEBPACK
    -0.75
     ostavi
    -0.72
     Meli
    -0.71
     مشين
    -0.70
    audiovisuel
    -0.69
    >--}}
    -0.67
    SceneManagement
    -0.66
     circonst
    -0.65
    /*
    -0.65
     AssemblyTitle
    -0.65
    POSITIVE LOGITS
     cracking
    0.95
    cra
    0.90
     crack
    0.89
    Cra
    0.89
     Cra
    0.81
     cracked
    0.80
     cracks
    0.80
     Cracker
    0.80
     Crack
    0.79
     Cracking
    0.78
    Activations Density 0.120%

    No Known Activations