© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 1077
    Prev
    Next
    INDEX
    Explanations

    terms related to crystal structures and crystallization processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CardBody
    -0.80
    enterOuterAlt
    -0.80
     IActionResult
    -0.76
    ไตล์
    -0.76
    imerick
    -0.74
     PLO
    -0.72
     ligation
    -0.72
     Norris
    -0.72
    LEADING
    -0.72
     Limerick
    -0.71
    POSITIVE LOGITS
     crystal
    2.52
     Crystal
    2.35
    crystal
    2.22
     crystals
    2.21
    Crystal
    2.19
     Crystals
    1.92
     kristal
    1.85
     cristal
    1.79
    YSTAL
    1.78
     криста
    1.51
    Activations Density 0.099%

    No Known Activations